Haifeng Wang


2022

pdf bib
DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering
Le Qi | Shangwen Lv | Hongyu Li | Jing Liu | Yu Zhang | Qiaoqiao She | Hua Wu | Haifeng Wang | Ting Liu
Findings of the Association for Computational Linguistics: ACL 2022

Open-domain question answering has been used in a wide range of applications, such as web search and enterprise search, which usually takes clean texts extracted from various formats of documents (e.g., web pages, PDFs, or Word documents) as the information source. However, designing different text extraction approaches is time-consuming and not scalable. In order to reduce human cost and improve the scalability of QA systems, we propose and study an Open-domain Document Visual Question Answering (Open-domain DocVQA) task, which requires answering questions based on a collection of document images directly instead of only document texts, utilizing layouts and visual features additionally. Towards this end, we introduce the first Chinese Open-domain DocVQA dataset called DuReadervis, containing about 15K question-answering pairs and 158K document images from the Baidu search engine. There are three main challenges in DuReadervis: (1) long document understanding, (2) noisy texts, and (3) multi-span answer extraction. The extensive experiments demonstrate that the dataset is challenging. Additionally, we propose a simple approach that incorporates the layout and visual features, and the experimental results show the effectiveness of the proposed approach. The dataset and code will be publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-vis.

pdf bib
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Xinchao Xu | Zhibin Gou | Wenquan Wu | Zheng-Yu Niu | Hua Wu | Haifeng Wang | Shihang Wang
Findings of the Association for Computational Linguistics: ACL 2022

Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework with Long-Term Memory (LTM) mechanism (called PLATO-LTM). This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring multiple-session dialogue datasets for model training. To our knowledge, this is the first attempt to conduct real-time dynamic management of persona information of both parties, including the user and the bot. Results on DuLeMon indicate that PLATO-LTM can significantly outperform baselines in terms of long-term dialogue consistency, leading to better dialogue engagingness.

pdf bib
UNIMO-2: End-to-End Unified Vision-Language Grounded Learning
Wei Li | Can Gao | Guocheng Niu | Xinyan Xiao | Hao Liu | Jiachen Liu | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: ACL 2022

Vision-Language Pre-training (VLP) has achieved impressive performance on various cross-modal downstream tasks. However, most existing methods can only learn from aligned image-caption data and rely heavily on expensive regional features, which greatly limits their scalability and performance. In this paper, we propose an end-to-end unified-modal pre-training framework, namely UNIMO-2, for joint learning on both aligned image-caption data and unaligned image-only and text-only corpus. We build a unified Transformer model to jointly learn visual representations, textual representations and semantic alignment between images and texts. In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora. The experiments show that our grounded learning method can improve textual and visual semantic alignment for improving performance on various cross-modal tasks. Moreover, benefiting from effective joint modeling of different types of corpora, our model also achieves impressive performance on single-modal visual and textual tasks. Our code and models are public at the UNIMO project page https://unimo-ptm.github.io/.

pdf bib
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang | Wenquan Wu | Zhihua Wu | Zhen Guo | Hua Lu | Xinxian Huang | Xin Tian | Xinchao Xu | Yingzhan Lin | Zheng-Yu Niu
Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022

To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conversations. To train such large models, we adopt the architecture of unified transformer with high computation and parameter efficiency. In addition, we carry out multi-party aware pre-training to better distinguish the characteristic information in social media conversations. With such designs, PLATO-XL successfully achieves superior performances as compared to other approaches in both Chinese and English chitchat. We further explore the capacity of PLATO-XL on other conversational tasks, such as knowledge grounded dialogue and task-oriented conversation. The experimental results indicate that PLATO-XL obtains state-of-the-art results across multiple conversational tasks, verifying its potential as a foundation model of conversational AI.

pdf bib
Findings of the Third Workshop on Automatic Simultaneous Translation
Ruiqing Zhang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Haifeng Wang | Liang Huang | Qun Liu | Julia Ive | Wolfgang Macherey
Proceedings of the Third Workshop on Automatic Simultaneous Translation

This paper reports the results of the shared task we hosted on the Third Workshop of Automatic Simultaneous Translation (AutoSimTrans). The shared task aims to promote the development of text-to-text and speech-to-text simultaneous translation, and includes Chinese-English and English-Spanish tracks. The number of systems submitted this year has increased fourfold compared with last year. Additionally, the top 1 ranked system in the speech-to-text track is the first end-to-end submission we have received in the past three years, which has shown great potential. This paper reports the results and descriptions of the 14 participating teams, compares different evaluation metrics, and revisits the ranking method.

pdf bib
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Pengzhi Gao | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut, a simple regularization method that forces the consistency between the output distributions of the original and the cutoff sentence pairs. Without leveraging extra dataset via back-translation or integrating large-scale pretrained model, Bi-SimCut achieves strong translation performance across five translation benchmarks (data sizes range from 160K to 20.2M): BLEU scores of 31.16 for \texttt{en}\texttt{de} and 38.37 for \texttt{de}\texttt{en} on the IWSLT14 dataset, 30.78 for \texttt{en}\texttt{de} and 35.15 for \texttt{de}\texttt{en} on the WMT14 dataset, and 27.17 for \texttt{zh}\texttt{en} on the WMT17 dataset. SimCut is not a new method, but a version of Cutoff (Shen et al., 2020) simplified and adapted for NMT, and it could be considered as a perturbation-based method. Given the universality and simplicity of Bi-SimCut and SimCut, we believe they can serve as strong baselines for future NMT research.

pdf bib
Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals
Zeming Liu | Jun Xu | Zeyang Lei | Haifeng Wang | Zheng-Yu Niu | Hua Wu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most dialog systems posit that users have figured out clear and specific goals before starting an interaction. For example, users have determined the departure, the destination, and the travel time for booking a flight. However, in many scenarios, limited by experience and knowledge, users may know what they need, but still struggle to figure out clear and specific goals by determining all the necessary slots. In this paper, we identify this challenge, and make a step forward by collecting a new human-to-human mixed-type dialog corpus. It contains 5k dialog sessions and 168k utterances for 4 dialog types and 5 domains. Within each session, an agent first provides user-goal-related knowledge to help figure out clear and specific goals, and then help achieve them. Furthermore, we propose a mixed-type dialog model with a novel Prompt-based continual learning mechanism. Specifically, the mechanism enables the model to continually strengthen its ability on any specific type by utilizing existing dialog corpora effectively.

pdf bib
Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation
Ruiqing Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

End-to-end simultaneous speech-to-text translation aims to directly perform translation from streaming source speech to target text with high translation quality and low latency. A typical simultaneous translation (ST) system consists of a speech translation model and a policy module, which determines when to wait and when to translate. Thus the policy is crucial to balance translation quality and latency. Conventional methods usually adopt fixed policies, e.g. segmenting the source speech with a fixed length and generating translation. However, this method ignores contextual information and suffers from low translation quality. This paper proposes an adaptive segmentation policy for end-to-end ST. Inspired by human interpreters, the policy learns to segment the source streaming speech into meaningful units by considering both acoustic features and translation history, maintaining consistency between the segmentation and translation. Experimental results on English-German and Chinese-English show that our method achieves a good accuracy-latency trade-off over recently proposed state-of-the-art methods.

2021

pdf bib
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora
Xuan Ouyang | Shuohuan Wang | Chao Pang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is generally acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose Ernie-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance. Our key insight is to integrate back-translation into the pre-training process. We generate pseudo-parallel sentence pairs on a monolingual corpus to enable the learning of semantic alignments between different languages, thereby enhancing the semantic modeling of cross-lingual models. Experimental results show that Ernie-M outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-lingual downstream tasks. The codes and pre-trained models will be made publicly available.

pdf bib
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
Ruiyang Ren | Yingqi Qu | Jing Liu | Wayne Xin Zhao | QiaoQiao She | Hua Wu | Haifeng Wang | Ji-Rong Wen
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly optimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage reranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dynamic distillation, the retriever and the re-ranker can be adaptively improved according to each other’s relevance information. We also propose a hybrid data augmentation strategy to construct diverse training instances for listwise training approach. Extensive experiments show the effectiveness of our approach on both MSMARCO and Natural Questions datasets. Our code is available at https://github.com/PaddlePaddle/RocketQA.

pdf bib
SgSum:Transforming Multi-document Summarization into Sub-graph Selection
Moye Chen | Wei Li | Jiachen Liu | Xinyan Xiao | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Most of existing extractive multi-document summarization (MDS) methods score each sentence individually and extract salient sentences one by one to compose a summary, which have two main drawbacks: (1) neglecting both the intra and cross-document relations between sentences; (2) neglecting the coherence and conciseness of the whole summary. In this paper, we propose a novel MDS framework (SgSum) to formulate the MDS task as a sub-graph selection problem, in which source documents are regarded as a relation graph of sentences (e.g., similarity graph or discourse graph) and the candidate summaries are its sub-graphs. Instead of selecting salient sentences, SgSum selects a salient sub-graph from the relation graph as the summary. Comparing with traditional methods, our method has two main advantages: (1) the relations between sentences are captured by modeling both the graph structure of the whole document set and the candidate sub-graphs; (2) directly outputs an integrate summary in the form of sub-graph which is more informative and coherent. Extensive experiments on MultiNews and DUC datasets show that our proposed method brings substantial improvements over several strong baselines. Human evaluation results also demonstrate that our model can produce significantly more coherent and informative summaries compared with traditional MDS methods. Moreover, the proposed architecture has strong transfer ability from single to multi-document input, which can reduce the resource bottleneck in MDS tasks.

pdf bib
DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation
Zeming Liu | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In this paper, we provide a bilingual parallel human-to-human recommendation dialog dataset (DuRecDial 2.0) to enable researchers to explore a challenging task of multilingual and cross-lingual conversational recommendation. The difference between DuRecDial 2.0 and existing conversational recommendation datasets is that the data item (Profile, Goal, Knowledge, Context, Response) in DuRecDial 2.0 is annotated in two languages, both English and Chinese, while other datasets are built with the setting of a single language. We collect 8.2k dialogs aligned across English and Chinese languages (16.5k dialogs and 255k utterances in total) that are annotated by crowdsourced workers with strict quality control procedure. We then build monolingual, multilingual, and cross-lingual conversational recommendation baselines on DuRecDial 2.0. Experiment results show that the use of additional English data can bring performance improvement for Chinese conversational recommendation, indicating the benefits of DuRecDial 2.0. Finally, this dataset provides a challenging testbed for future studies of monolingual, multilingual, and cross-lingual conversational recommendation.

pdf bib
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing
Kun Wu | Lijie Wang | Zhenghua Li | Ao Zhang | Xinyan Xiao | Hua Wu | Min Zhang | Haifeng Wang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Data augmentation has attracted a lot of research attention in the deep learning era for its ability in alleviating data sparseness. The lack of labeled data for unseen evaluation databases is exactly the major challenge for cross-domain text-to-SQL parsing. Previous works either require human intervention to guarantee the quality of generated data, or fail to handle complex SQL queries. This paper presents a simple yet effective data augmentation framework. First, given a database, we automatically produce a large number of SQL queries based on an abstract syntax tree grammar. For better distribution matching, we require that at least 80% of SQL patterns in the training data are covered by generated queries. Second, we propose a hierarchical SQL-to-question generation model to obtain high-quality natural language questions, which is the major contribution of this work. Finally, we design a simple sampling strategy that can greatly improve training efficiency given large amounts of generated data. Experiments on three cross-domain datasets, i.e., WikiSQL and Spider in English, and DuSQL in Chinese, show that our proposed data augmentation framework can consistently improve performance over strong baselines, and the hierarchical generation component is the key for the improvement.

pdf bib
PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling
Xinxian Huang | Huang He | Siqi Bao | Fan Wang | Hua Wu | Haifeng Wang
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI

Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation. Considering the infeasibility to annotate the external knowledge for large-scale dialogue corpora, it is desirable to learn the knowledge selection and response generation in an unsupervised manner. In this paper, we propose PLATO-KAG (Knowledge-Augmented Generation), an unsupervised learning approach for end-to-end knowledge-grounded conversation modeling. For each dialogue context, the top-k relevant knowledge elements are selected and then employed in knowledge-grounded response generation. The two components of knowledge selection and response generation are optimized jointly and effectively under a balanced objective. Experimental results on two publicly available datasets validate the superiority of PLATO-KAG.

pdf bib
Proceedings of the Second Workshop on Automatic Simultaneous Translation
Hua Wu | Colin Cherry | Liang Huang | Zhongjun He | Qun Liu | Maha Elbayad | Mark Liberman | Haifeng Wang | Mingbo Ma | Ruiqing Zhang
Proceedings of the Second Workshop on Automatic Simultaneous Translation

pdf bib
BSTC: A Large-Scale Chinese-English Speech Translation Dataset
Ruiqing Zhang | Xiyang Wang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Zhi Li | Haifeng Wang | Ying Chen | Qinfei Li
Proceedings of the Second Workshop on Automatic Simultaneous Translation

This paper presents BSTC (Baidu Speech Translation Corpus), a large-scale Chinese-English speech translation dataset. This dataset is constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of Mandarin data, their manual transcripts and translations into English, as well as automated transcripts by an automatic speech recognition (ASR) model. We have further asked three experienced interpreters to simultaneously interpret the testing talks in a mock conference setting. This corpus is expected to promote the research of automatic simultaneous translation as well as the development of practical systems. We have organized simultaneous translation tasks and used this corpus to evaluate automatic simultaneous translation systems.

pdf bib
Findings of the Second Workshop on Automatic Simultaneous Translation
Ruiqing Zhang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the Second Workshop on Automatic Simultaneous Translation

This paper presents the results of the shared task of the 2nd Workshop on Automatic Simultaneous Translation (AutoSimTrans). The task includes two tracks, one for text-to-text translation and one for speech-to-text, requiring participants to build systems to translate from either the source text or speech into the target text. Different from traditional machine translation, the AutoSimTrans shared task evaluates not only translation quality but also latency. We propose a metric “Monotonic Optimal Sequence” (MOS) considering both quality and latency to rank the submissions. We also discuss some important open issues in simultaneous translation.

pdf bib
Link Prediction on N-ary Relational Facts: A Graph-based Approach
Quan Wang | Haifeng Wang | Yajuan Lyu | Yong Zhu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
Ruiyang Ren | Shangwen Lv | Yingqi Qu | Jing Liu | Wayne Xin Zhao | QiaoQiao She | Hua Wu | Haifeng Wang | Ji-Rong Wen
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Correcting Chinese Spelling Errors with Phonetic Pre-training
Ruiqing Zhang | Chao Pang | Chuanqiang Zhang | Shuohuan Wang | Zhongjun He | Yu Sun | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang | Wenquan Wu | Zhen Guo | Zhibin Liu | Xinchao Xu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Mixup Decoding for Diverse Machine Translation
Jicheng Li | Pengzhi Gao | Xuanfu Wu | Yang Feng | Zhongjun He | Hua Wu | Haifeng Wang
Findings of the Association for Computational Linguistics: EMNLP 2021

Diverse machine translation aims at generating various target language translations for a given source language sentence. To leverage the linear relationship in the sentence latent space introduced by the mixup training, we propose a novel method, MixDiversity, to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding. To further improve the faithfulness and diversity of the translations, we propose two simple but effective approaches to select diverse sentence pairs in the training corpus and adjust the interpolation weight for each pair correspondingly. Moreover, by controlling the interpolation weight, our method can achieve the trade-off between faithfulness and diversity without any additional training, which is required in most of the previous methods. Experiments on WMT’16 en-ro, WMT’14 en-de, and WMT’17 zh-en are conducted to show that our method substantially outperforms all previous diverse machine translation methods.

pdf bib
Discovering Dialog Structure Graph for Coherent Dialog Generation
Jun Xu | Zeyang Lei | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Learning discrete dialog structure graph from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation. However, this problem is less studied in open-domain dialogue. In this paper, we conduct unsupervised discovery of discrete dialog structure from chitchat corpora, and then leverage it to facilitate coherent dialog generation in downstream systems. To this end, we present an unsupervised model, Discrete Variational Auto-Encoder with Graph Neural Network (DVAE-GNN), to discover discrete hierarchical latent dialog states (at the level of both session and utterance) and their transitions from corpus as a dialog structure graph. Then we leverage it as background knowledge to facilitate dialog management in a RL based dialog system. Experimental results on two benchmark corpora confirm that DVAE-GNN can discover meaningful dialog structure graph, and the use of dialog structure as background knowledge can significantly improve multi-turn coherence.

pdf bib
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning
Wei Li | Can Gao | Guocheng Niu | Xinyan Xiao | Hao Liu | Jiachen Liu | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e., text or image) or limited multi-modal data (i.e., image-text pairs). In this work, we propose a UNIfied-MOdal pre-training architecture, namely UNIMO, which can effectively adapt to both single-modal and multi-modal understanding and generation tasks. Large scale of free text corpus and image collections are utilized to improve the capability of visual and textual understanding, and cross-modal contrastive learning (CMCL) is leveraged to align the textual and visual information into a unified semantic space, over a corpus of image-text pairs augmented with related images and texts. With the help of rich non-paired single-modal data, our model is able to learn more generalizable representations, by allowing textual knowledge and visual knowledge to enhance each other in the unified semantic space. The experimental results show that UNIMO greatly improves the performance of several single-modal and multi-modal downstream tasks. Our code and pre-trained models are public at https://github.com/PaddlePaddle/Research/tree/master/NLP/UNIMO.

pdf bib
ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
SiYu Ding | Junyuan Shang | Shuohuan Wang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption. Simply truncating a long document or applying the sparse attention mechanism will incur the context fragmentation problem or lead to an inferior modeling capability against comparable model sizes. In this paper, we propose ERNIE-Doc, a document-level language pretraining model based on Recurrence Transformers. Two well-designed techniques, namely the retrospective feed mechanism and the enhanced recurrence mechanism, enable ERNIE-Doc, which has a much longer effective context length, to capture the contextual information of a complete document. We pretrain ERNIE-Doc to explicitly learn the relationships among segments with an additional document-aware segment-reordering objective. Various experiments were conducted on both English and Chinese document-level tasks. ERNIE-Doc improved the state-of-the-art language modeling result of perplexity to 16.8 on WikiText-103. Moreover, it outperformed competitive pretraining models by a large margin on most language understanding tasks, such as text classification and question answering.

pdf bib
BASS: Boosting Abstractive Summarization with Unified Semantic Graph
Wenhao Wu | Wei Li | Xinyan Xiao | Jiachen Liu | Ziqiang Cao | Sujian Li | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Abstractive summarization for long-document or multi-document remains challenging for the Seq2Seq architecture, as Seq2Seq is not good at analyzing long-distance relations in text. In this paper, we present BASS, a novel framework for Boosting Abstractive Summarization based on a unified Semantic graph, which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases. Further, a graph-based encoder-decoder model is proposed to improve both the document representation and summary generation process by leveraging the graph structure. Specifically, several graph augmentation methods are designed to encode both the explicit and implicit relations in the text while the graph-propagation attention mechanism is developed in the decoder to select salient content into the summary. Empirical results show that the proposed architecture brings substantial improvements for both long-document and multi-document summarization tasks.

pdf bib
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
Hongxuan Tang | Hongyu Li | Jing Liu | Yu Hong | Hua Wu | Haifeng Wang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements. However, most of the neural MRC models are still far from robust and fail to generalize well in real-world applications. In order to comprehensively verify the robustness and generalization of MRC models, we introduce a real-world Chinese dataset – DuReader_robust . It is designed to evaluate the MRC models from three aspects: over-sensitivity, over-stability and generalization. Comparing to previous work, the instances in DuReader_robust are natural texts, rather than the altered unnatural texts. It presents the challenges when applying MRC models to real-world applications. The experimental results show that MRC models do not perform well on the challenge test set. Moreover, we analyze the behavior of existing models on the challenge test set, which may provide suggestions for future model development. The dataset and codes are publicly available at https://github.com/baidu/DuReader.

pdf bib
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
Dongling Xiao | Yu-Kun Li | Han Zhang | Yu Sun | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Coarse-grained linguistic information, such as named entities or phrases, facilitates adequately representation learning in pre-training. Previous works mainly focus on extending the objective of BERT’s Masked Language Modeling (MLM) from masking individual tokens to contiguous sequences of n tokens. We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information. As an alternative, we propose ERNIE-Gram, an explicitly n-gram masking method to enhance the integration of coarse-grained information into pre-training. In ERNIE-Gram, n-grams are masked and predicted directly using explicit n-gram identities rather than contiguous sequences of n tokens. Furthermore, ERNIE-Gram employs a generator model to sample plausible n-gram identities as optional n-gram masks and predict them in both coarse-grained and fine-grained manners to enable comprehensive n-gram prediction and relation modeling. We pre-train ERNIE-Gram on English and Chinese text corpora and fine-tune on 19 downstream tasks. Experimental results show that ERNIE-Gram outperforms previous pre-training models like XLNet and RoBERTa by a large margin, and achieves comparable results with state-of-the-art methods. The source codes and pre-trained models have been released at https://github.com/PaddlePaddle/ERNIE.

pdf bib
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
Yingqi Qu | Yuchen Ding | Jing Liu | Kai Liu | Ruiyang Ren | Wayne Xin Zhao | Daxiang Dong | Hua Wu | Haifeng Wang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and passages for semantic matching. However, it is difficult to effectively train a dual-encoder due to the challenges including the discrepancy between training and inference, the existence of unlabeled positives and limited training data. To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. We make three major technical contributions in RocketQA, namely cross-batch negatives, denoised hard negatives and data augmentation. The experiment results show that RocketQA significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions. We also conduct extensive experiments to examine the effectiveness of the three strategies in RocketQA. Besides, we demonstrate that the performance of end-to-end QA can be improved based on our RocketQA retriever.

2020

pdf bib
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
Siqi Bao | Huang He | Fan Wang | Hua Wu | Haifeng Wang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering. In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation. We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation. Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network. Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.

pdf bib
Towards Conversational Recommendation over Multi-Type Dialogs
Zeming Liu | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che | Ting Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

We focus on the study of conversational recommendation in the context of multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e.g., QA) to a recommendation dialog, taking into account user’s interests and feedback. To facilitate the study of this task, we create a human-to-human Chinese dialog dataset DuRecDial (about 10k dialogs, 156k utterances), where there are multiple sequential dialogs for a pair of a recommendation seeker (user) and a recommender (bot). In each dialog, the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior. This dataset allows us to systematically investigate different parts of the overall problem, e.g., how to naturally lead a dialog, how to interact with users for recommendation. Finally we establish baseline results on DuRecDial for future studies.

pdf bib
Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation
Jun Xu | Haifeng Wang | Zheng-Yu Niu | Hua Wu | Wanxiang Che | Ting Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

To address the challenge of policy learning in open-domain multi-turn conversation, we propose to represent prior information about dialog transitions as a graph and learn a graph grounded dialog policy, aimed at fostering a more coherent and controllable dialog. To this end, we first construct a conversational graph (CG) from dialog corpora, in which there are vertices to represent “what to say” and “how to say”, and edges to represent natural transition between a message (the last utterance in a dialog context) and its response. We then present a novel CG grounded policy learning framework that conducts dialog flow planning by graph traversal, which learns to identify a what-vertex and a how-vertex from the CG at each turn to guide response generation. In this way, we effectively leverage the CG to facilitate policy learning as follows: (1) it enables more effective long-term reward design, (2) it provides high-quality candidate actions, and (3) it gives us more control over the policy. Results on two benchmark corpora demonstrate the effectiveness of this framework.

pdf bib
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis
Hao Tian | Can Gao | Xinyan Xiao | Hao Liu | Bolei He | Hua Wu | Haifeng Wang | Feng Wu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Recently, sentiment analysis has seen remarkable advance with the help of pre-training approaches. However, sentiment knowledge, such as sentiment words and aspect-sentiment pairs, is ignored in the process of pre-training, despite the fact that they are widely used in traditional sentiment analysis approaches. In this paper, we introduce Sentiment Knowledge Enhanced Pre-training (SKEP) in order to learn a unified sentiment representation for multiple sentiment analysis tasks. With the help of automatically-mined knowledge, SKEP conducts sentiment masking and constructs three sentiment knowledge prediction objectives, so as to embed sentiment information at the word, polarity and aspect level into pre-trained sentiment representation. In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair. Experiments on three kinds of sentiment tasks show that SKEP significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets. We release our code at https://github.com/baidu/Senta.

pdf bib
Leveraging Graph to Improve Abstractive Multi-Document Summarization
Wei Li | Xinyan Xiao | Jiachen Liu | Hua Wu | Haifeng Wang | Junping Du
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries. Furthermore, pre-trained language models can be easily combined with our model, which further improve the summarization performance significantly. Empirical results on the WikiSum and MultiNews dataset show that the proposed architecture brings substantial improvements over several strong baselines.

pdf bib
Learning Adaptive Segmentation Policy for Simultaneous Translation
Ruiqing Zhang | Chuanqiang Zhang | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Balancing accuracy and latency is a great challenge for simultaneous translation. To achieve high accuracy, the model usually needs to wait for more streaming text before translation, which results in increased latency. However, keeping low latency would probably hurt accuracy. Therefore, it is essential to segment the ASR output into appropriate units for translation. Inspired by human interpreters, we propose a novel adaptive segmentation policy for simultaneous translation. The policy learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation. Experimental results on Chinese-English and German-English translation show that our method achieves a better accuracy-latency trade-off over recently proposed state-of-the-art methods.

pdf bib
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
Lijie Wang | Ao Zhang | Kun Wu | Ke Sun | Zhenghua Li | Hua Wu | Min Zhang | Haifeng Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Due to the lack of labeled data, previous research on text-to-SQL parsing mainly focuses on English. Representative English datasets include ATIS, WikiSQL, Spider, etc. This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs. Our new dataset has three major characteristics. First, by manually analyzing questions from several representative applications, we try to figure out the true distribution of SQL queries in real-life needs. Second, DuSQL contains a considerable proportion of SQL queries involving row or column calculations, motivated by our analysis on the SQL query distributions. Finally, we adopt an effective data construction framework via human-computer collaboration. The basic idea is automatically generating SQL queries based on the SQL grammar and constrained by the given database. This paper describes in detail the construction process and data statistics of DuSQL. Moreover, we present and compare performance of several open-source text-to-SQL parsers with minor modification to accommodate Chinese, including a simple yet effective extension to IRNet for handling calculation SQL queries.

2019

pdf bib
Multi-agent Learning for Neural Machine Translation
Tianchi Bi | Hao Xiong | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decod- ing from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent sce- nario by introducing diverse agents in an in- teractive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline sys- tems and shows competitive performance on all tasks.

pdf bib
Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs
Zhibin Liu | Zheng-Yu Niu | Hua Wu | Haifeng Wang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Two types of knowledge, triples from knowledge graphs and texts from documents, have been studied for knowledge aware open domain conversation generation, in which graph paths can narrow down vertex candidates for knowledge selection decision, and texts can provide rich information for response generation. Fusion of a knowledge graph and texts might yield mutually reinforcing advantages, but there is less study on that. To address this challenge, we propose a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator. For knowledge selection on the graph, we formulate it as a problem of multi-hop graph reasoning to effectively capture conversation flow, which is more explainable and flexible in comparison with previous works. To fully leverage long text information that differentiates our graph from others, we improve a state of the art reasoning algorithm with machine reading comprehension technology. We demonstrate the effectiveness of our system on two datasets in comparison with state-of-the-art models.

pdf bib
D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension
Hongyu Li | Xiyuan Zhang | Yibing Liu | Yiming Zhang | Quan Wang | Xiangyang Zhou | Jing Liu | Hua Wu | Haifeng Wang
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models. Our system is built on a framework of pretraining and fine-tuning, namely D-NET. The techniques of pre-trained language models and multi-task learning are explored to improve the generalization of MRC models and we conduct experiments to examine the effectiveness of these strategies. Our system is ranked at top 1 of all the participants in terms of averaged F1 score. Our codes and models will be released at PaddleNLP.

pdf bib
Baidu Neural Machine Translation Systems for WMT19
Meng Sun | Bojian Jiang | Hao Xiong | Zhongjun He | Hua Wu | Haifeng Wang
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

In this paper we introduce the systems Baidu submitted for the WMT19 shared task on Chinese<->English news translation. Our systems are based on the Transformer architecture with some effective improvements. Data selection, back translation, data augmentation, knowledge distillation, domain adaptation, model ensemble and re-ranking are employed and proven effective in our experiments. Our Chinese->English system achieved the highest case-sensitive BLEU score among all constrained submissions, and our English->Chinese system ranked the second in all submissions.

pdf bib
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
Mingbo Ma | Liang Huang | Hao Xiong | Renjie Zheng | Kaibo Liu | Baigong Zheng | Chuanqiang Zhang | Zhongjun He | Hairong Liu | Xing Li | Hua Wu | Haifeng Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Simultaneous translation, which translates sentences before they are finished, is use- ful in many scenarios but is notoriously dif- ficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we pro- pose a novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very sim- ple yet surprisingly effective “wait-k” policy trained to generate the target sentence concur- rently with the source sentence, but always k words behind. Experiments show our strat- egy achieves low latency and reasonable qual- ity (compared to full-sentence translation) on 4 directions: zh↔en and de↔en.

pdf bib
Proactive Human-Machine Conversation with Explicit Conversation Goal
Wenquan Wu | Zhen Guo | Xiangyang Zhou | Hua Wu | Xiyuan Zhang | Rongzhong Lian | Haifeng Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Though great progress has been made for human-machine conversation, current dialogue system is still in its infancy: it usually converses passively and utters words more as a matter of response, rather than on its own initiatives. In this paper, we take a radical step towards building a human-like conversational agent: endowing it with the ability of proactively leading the conversation (introducing a new topic or maintaining the current topic). To facilitate the development of such conversation systems, we create a new dataset named Konv where one acts as a conversation leader and the other acts as the follower. The leader is provided with a knowledge graph and asked to sequentially change the discussion topics, following the given conversation goal, and meanwhile keep the dialogue as natural and engaging as possible. Konv enables a very challenging task as the model needs to both understand dialogue and plan over the given knowledge graph. We establish baseline results on this dataset (about 270K utterances and 30k dialogues) using several state-of-the-art models. Experimental results show that dialogue models that plan over the knowledge graph can make full use of related knowledge to generate more diverse multi-turn conversations. The baseline systems along with the dataset are publicly available.

2018

pdf bib
DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
Wei He | Kai Liu | Jing Liu | Yajuan Lyu | Shiqi Zhao | Xinyan Xiao | Yuan Liu | Yizhong Wang | Hua Wu | Qiaoqiao She | Xuan Liu | Tian Wu | Haifeng Wang
Proceedings of the Workshop on Machine Reading for Question Answering

This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC. DuReader has three advantages over previous MRC datasets: (1) data sources: questions and documents are based on Baidu Search and Baidu Zhidao; answers are manually generated. (2) question types: it provides rich annotations for more question types, especially yes-no and opinion questions, that leaves more opportunity for the research community. (3) scale: it contains 200K questions, 420K answers and 1M documents; it is the largest Chinese MRC dataset so far. Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements. To help the community make these improvements, both DuReader and baseline systems have been posted online. We also organize a shared competition to encourage the exploration of more models. Since the release of the task, there are significant improvements over the baselines.

pdf bib
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
Yizhong Wang | Kai Liu | Jing Liu | Wei He | Yajuan Lyu | Hua Wu | Sujian Li | Haifeng Wang
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine. Compared with MRC on a single passage, multi-passage MRC is more challenging, since we are likely to get multiple confusing answer candidates from different passages. To address this problem, we propose an end-to-end neural model that enables those answer candidates from different passages to verify each other based on their content representations. Specifically, we jointly train three modules that can predict the final answer based on three factors: the answer boundary, the answer content and the cross-passage answer verification. The experimental results show that our method outperforms the baseline by a large margin and achieves the state-of-the-art performance on the English MS-MARCO dataset and the Chinese DuReader dataset, both of which are designed for MRC in real-world settings.

2017

pdf bib
Multi-task Attention-based Neural Networks for Implicit Discourse Relationship Representation and Identification
Man Lan | Jianxiang Wang | Yuanbin Wu | Zheng-Yu Niu | Haifeng Wang
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

We present a novel multi-task attention based neural network model to address implicit discourse relationship representation and identification through two types of representation learning, an attention based neural network for learning discourse relationship representation with two arguments and a multi-task framework for learning knowledge from annotated and unannotated corpora. The extensive experiments have been performed on two benchmark corpora (i.e., PDTB and CoNLL-2016 datasets). Experimental results show that our proposed model outperforms the state-of-the-art systems on benchmark corpora.

2016

pdf bib
Active Learning for Dependency Parsing with Partial Annotation
Zhenghua Li | Min Zhang | Yue Zhang | Zhanyi Liu | Wenliang Chen | Hua Wu | Haifeng Wang
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
A Universal Framework for Inductive Transfer Parsing across Multi-typed Treebanks
Jiang Guo | Wanxiang Che | Haifeng Wang | Ting Liu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain common syntactic knowledge that is potential to benefit each other. This paper presents a universal framework for transfer parsing across multi-typed treebanks with deep multi-task learning. We consider two kinds of treebanks as source: the multilingual universal treebanks and the monolingual heterogeneous treebanks. Knowledge across the source and target treebanks are effectively transferred through multi-level parameter sharing. Experiments on several benchmark datasets in various languages demonstrate that our approach can make effective use of arbitrary source treebanks to improve target parsing models.

pdf bib
Chinese Poetry Generation with Planning based Neural Network
Zhe Wang | Wei He | Hua Wu | Haiyang Wu | Wei Li | Haifeng Wang | Enhong Chen
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Chinese poetry generation is a very challenging task in natural language processing. In this paper, we propose a novel two-stage poetry generating method which first plans the sub-topics of the poem according to the user’s writing intent, and then generates each line of the poem sequentially, using a modified recurrent neural network encoder-decoder framework. The proposed planning-based method can ensure that the generated poem is coherent and semantically consistent with the user’s intent. A comprehensive evaluation with human judgments demonstrates that our proposed approach outperforms the state-of-the-art poetry generating methods and the poem quality is somehow comparable to human poets.

pdf bib
A Unified Architecture for Semantic Role Labeling and Relation Classification
Jiang Guo | Wanxiang Che | Haifeng Wang | Ting Liu | Jun Xu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

This paper describes a unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence. We investigate two typical and well-studied tasks: semantic role labeling (SRL) which identifies the relations between predicates and arguments, and relation classification (RC) which focuses on the relation between two entities or nominals. While mostly studied separately in prior work, we show that the two tasks can be effectively connected and modeled using a general architecture. Experiments on CoNLL-2009 benchmark datasets show that our SRL models significantly outperform state-of-the-art approaches. Our RC models also yield competitive performance with the best published records. Furthermore, we show that the two tasks can be trained jointly with multi-task learning, resulting in additive significant improvements for SRL.

2015

pdf bib
Improved beam search with constrained softmax for NMT
Xiaoguang Hu | Wei Li | Xiang Lan | Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit XV: Papers

pdf bib
Cross-lingual Dependency Parsing Based on Distributed Representations
Jiang Guo | Wanxiang Che | David Yarowsky | Haifeng Wang | Ting Liu
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
Multi-Task Learning for Multiple Language Translation
Daxiang Dong | Hua Wu | Wei He | Dianhai Yu | Haifeng Wang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System
Zhuoran Wang | Hongliang Chen | Guanchun Wang | Hao Tian | Hua Wu | Haifeng Wang
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Revisiting Embedding Features for Simple Semi-supervised Learning
Jiang Guo | Wanxiang Che | Haifeng Wang | Ting Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Improve Statistical Machine Translation with Context-Sensitive Bilingual Semantic Embedding Model
Haiyang Wu | Daxiang Dong | Xiaoguang Hu | Dianhai Yu | Wei He | Hua Wu | Haifeng Wang | Ting Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Transformation from Discontinuous to Continuous Word Alignment Improves Translation Quality
Zhongjun He | Hua Wu | Haifeng Wang | Ting Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs
Xiaoning Zhu | Zhongjun He | Hua Wu | Conghui Zhu | Haifeng Wang | Tiejun Zhao
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources
Jiang Guo | Wanxiang Che | Haifeng Wang | Ting Liu
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Learning Semantic Hierarchies via Word Embeddings
Ruiji Fu | Jiang Guo | Bing Qin | Wanxiang Che | Haifeng Wang | Ting Liu
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2013

pdf bib
Generalization of Words for Chinese Dependency Parsing
Xianchao Wu | Jie Zhou | Yu Sun | Zhanyi Liu | Dianhai Yu | Hua Wu | Haifeng Wang
Proceedings of the 13th International Conference on Parsing Technologies (IWPT 2013)

pdf bib
Improving Pivot-Based Statistical Machine Translation Using Random Walk
Xiaoning Zhu | Zhongjun He | Hua Wu | Haifeng Wang | Conghui Zhu | Tiejun Zhao
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Bootstrapping Large-scale Named Entities using URL-Text Hybrid Patterns
Chao Zhang | Shiqi Zhao | Haifeng Wang
Proceedings of the Sixth International Joint Conference on Natural Language Processing

pdf bib
A Hierarchical Semantics-Aware Distributional Similarity Scheme
Shuqi Sun | Ke Sun | Shiqi Zhao | Haifeng Wang | Muyun Yang | Sheng Li
Proceedings of the Sixth International Joint Conference on Natural Language Processing

2012

pdf bib
Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information
Jinsong Su | Hua Wu | Haifeng Wang | Yidong Chen | Xiaodong Shi | Huailin Dong | Qun Liu
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Improve SMT Quality with Automatically Extracted Paraphrase Rules
Wei He | Hua Wu | Haifeng Wang | Ting Liu
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
User Behaviors Lend a Helping Hand: Learning Paraphrase Query Patterns from Search Log Sessions
Shiqi Zhao | Haifeng Wang | Ting Liu
Proceedings of COLING 2012

2011

pdf bib
Reordering with Source Language Collocations
Zhanyi Liu | Haifeng Wang | Hua Wu | Ting Liu | Sheng Li
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Proceedings of 5th International Joint Conference on Natural Language Processing
Haifeng Wang | David Yarowsky
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
Enriching SMT Training Data via Paraphrasing
Wei He | Shiqi Zhao | Haifeng Wang | Ting Liu
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
Automatically Generating Questions from Queries for Community-based Question Answering
Shiqi Zhao | Haifeng Wang | Chao Li | Ting Liu | Yi Guan
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
Harvesting Related Entities with a Search Engine
Shuqi Sun | Shiqi Zhao | Muyun Yang | Haifeng Wang | Sheng Li
Proceedings of 5th International Joint Conference on Natural Language Processing

pdf bib
Web-based Machine Translation
Haifeng Wang
Proceedings of the Fifth International Workshop On Cross Lingual Information Access

2010

pdf bib
Improving Statistical Machine Translation with Monolingual Collocation
Zhanyi Liu | Haifeng Wang | Hua Wu | Sheng Li
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
Lluís Màrquez | Haifeng Wang
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

pdf bib
Paraphrasing with Search Engine Query Logs
Shiqi Zhao | Haifeng Wang | Ting Liu
Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)

pdf bib
Leveraging Multiple MT Engines for Paraphrase Generation
Shiqi Zhao | Haifeng Wang | Xiang Lan | Ting Liu
Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)

pdf bib
Coling 2010: Paraphrases and Applications–Tutorial notes
Shiqi Zhao | Haifeng Wang
Coling 2010: Paraphrases and Applications–Tutorial notes

pdf bib
Paraphrases and Applications
Shiqi Zhao | Haifeng Wang
Coling 2010: Paraphrases and Applications–Tutorial notes

2009

pdf bib
Exploiting Heterogeneous Treebanks for Parsing
Zheng-Yu Niu | Haifeng Wang | Hua Wu
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
Revisiting Pivot Language Approach for Machine Translation
Hua Wu | Haifeng Wang
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
Dependency Based Chinese Sentence Realization
Wei He | Haifeng Wang | Yuqing Guo | Ting Liu
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
Collocation Extraction Using Monolingual Word Alignment Method
Zhanyi Liu | Haifeng Wang | Hua Wu | Sheng Li
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

2008

pdf bib
Dependency-Based N-Gram Models for General Purpose Sentence Realisation
Yuqing Guo | Josef van Genabith | Haifeng Wang
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Prediction of Maximal Projection for Semantic Role Labeling
Weiwei Sun | Zhifang Sui | Haifeng Wang
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Domain Adaptation for Statistical Machine Translation with Domain Dictionary and Monolingual Corpora
Hua Wu | Haifeng Wang | Chengqing Zong
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Pivot Approach for Extracting Paraphrase Patterns from Bilingual Corpora
Shiqi Zhao | Haifeng Wang | Ting Liu | Sheng Li
Proceedings of ACL-08: HLT

pdf bib
The TCH machine translation system for IWSLT 2008.
Haifeng Wang | Hua Wu | Xiaoguang Hu | Zhanyi Liu | Jianfeng Li | Dengjun Ren | Zhengyu Niu
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

This paper reports on the first participation of TCH (Toshiba (China) Research and Development Center) at the IWSLT evaluation campaign. We participated in all the 5 translation tasks with Chinese as source language or target language. For Chinese-English and English-Chinese translation, we used hybrid systems that combine rule-based machine translation (RBMT) method and statistical machine translation (SMT) method. For Chinese-Spanish translation, phrase-based SMT models were used. For the pivot task, we combined the translations generated by a pivot based statistical translation model and a statistical transfer translation model (firstly, translating from Chinese to English, and then from English to Spanish). Moreover, for better performance of MT, we improved each module in the MT systems as follows: adapting Chinese word segmentation to spoken language translation, selecting out-of-domain corpus to build language models, using bilingual dictionaries to correct word alignment results, handling NE translation and selecting translations from the outputs of multiple systems. According to the automatic evaluation results on the full test sets, we top in all the 5 tasks.

pdf bib
Accurate and Robust LFG-Based Generation for Chinese
Yuqing Guo | Haifeng Wang | Josef van Genabith
Proceedings of the Fifth International Natural Language Generation Conference

2007

pdf bib
Pivot Language Approach for Phrase-Based Statistical Machine Translation
Hua Wu | Haifeng Wang
Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics

pdf bib
Recovering Non-Local Dependencies for Chinese
Yuqing Guo | Haifeng Wang | Josef van Genabith
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf bib
Using RBMT Systems to Produce Bilingual Corpus for SMT
Xiaoguang Hu | Haifeng Wang | Hua Wu
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

pdf bib
Improving statistical word alignment with various clues
Dengjun Ren | Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit XI: Papers

pdf bib
Comparative study of word alignment heuristics and phrase-based SMT
Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit XI: Papers

2006

pdf bib
An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation
Zhimao Lu | Haifeng Wang | Jianmin Yao | Ting Liu | Sheng Li
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
The Effect of Translation Quality in MT-Based Cross-Language Information Retrieval
Jiang Zhu | Haifeng Wang
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
Discriminative Pruning of Language Models for Chinese Word Segmentation
Jianfeng Li | Haifeng Wang | Dengjun Ren | Guohua Li
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
Word Alignment for Languages with Scarce Resources Using Bilingual Corpora of Other Language Pairs
Haifeng Wang | Hua Wu | Zhanyi Liu
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf bib
Boosting Statistical Word Alignment Using Labeled and Unlabeled Data
Hua Wu | Haifeng Wang | Zhanyi Liu
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

2005

pdf bib
Improving Statistical Word Alignment with Ensemble Methods
Hua Wu | Haifeng Wang
Second International Joint Conference on Natural Language Processing: Full Papers

pdf bib
Alignment Model Adaptation for Domain-Specific Word Alignment
Hua Wu | Haifeng Wang | Zhanyi Liu
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05)

pdf bib
Example-based Machine Translation Based on TSC and Statistical Generation
Zhanyi Liu | Haifeng Wang | Hua Wu
Proceedings of Machine Translation Summit X: Papers

This paper proposes a novel Example-Based Machine Translation (EBMT) method based on Tree String Correspondence (TSC) and statistical generation. In this method, the translation examples are represented as TSC, which consists of three parts: a parse tree in the source language, a string in the target language, and the correspondences between the leaf nodes of the source language tree and the substrings of the target language string. During the translation, the input sentence is first parsed into a tree. Then the TSC forest is searched out if it is best matched with the parse tree. The translation is generated by using a statistical generation model to combine the target language strings in the TSCs. The generation model consists of three parts: the semantic similarity between words, the word translation probability, and the target language model. Based on the above method, we build an English-to-Chinese Machine Translation (ECMT) system. Experimental results indicate that the performance of our system is comparable with that of the state-of-the-art commercial ECMT systems.

pdf bib
Boosting Statistical Word Alignment
Hua Wu | Haifeng Wang
Proceedings of Machine Translation Summit X: Papers

This paper proposes an approach to improve statistical word alignment with the boosting method. Applying boosting to word alignment must solve two problems. The first is how to build the reference set for the training data. We propose an approach to automatically build a pseudo reference set, which can avoid manual annotation of the training set. The second is how to calculate the error rate of each individual word aligner. We solve this by calculating the error rate of a manually annotated held-out data set instead of the entire training set. In addition, the final ensemble takes into account the weights of the alignment links produced by the individual word aligners. Experimental results indicate that the boosting method proposed in this paper performs much better than the original word aligner, achieving a large error rate reduction.

pdf bib
Improving Translation Memory with Word Alignment Information
Hua Wu | Haifeng Wang | Zhanyi Liu | Kai Tang
Proceedings of Machine Translation Summit X: Posters

This paper describes a generalized translation memory system, which takes advantage of sentence level matching, sub-sentential matching, and pattern-based machine translation technologies. All of the three techniques generate translation suggestions with the assistance of word alignment information. For the sentence level matching, the system generates the translation suggestion by modifying the translations of the most similar example with word alignment information. For sub-sentential matching, the system locates the translation fragments in several examples with word alignment information, and then generates the translation suggestion by combining these translation fragments. For pattern-based machine translation, the system first extracts translation patterns from examples using word alignment information and then generates translation suggestions with pattern matching. This system is compared with a traditional translation memory system without word alignment information in terms of translation efficiency and quality. Evaluation results indicate that our system improves the translation quality and saves about 20% translation time.

2004

pdf bib
Improving Domain-Specific Word Alignment for Computer Assisted Translation
Hua Wu | Haifeng Wang
Proceedings of the ACL Interactive Poster and Demonstration Sessions

pdf bib
Improving domain-specific word alignment with a general bilingual corpus
Hua Wu | Haifeng Wang
Proceedings of the 6th Conference of the Association for Machine Translation in the Americas: Technical Papers

In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentence-aligned training corpora. Others employ dictionaries to guide alignment selection. However, these methods achieve unsatisfactory alignment results when performing word alignment on a small-scale domain-specific bilingual corpus without terminological lexicons. This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain. This approach first trains two statistical word alignment models with the large-scale corpus in the general domain and the small-scale corpus in the specific domain respectively, and then improves the domain-specific word alignment with these two models. Experimental results show a significant improvement in terms of both alignment precision and recall, achieving a relative error rate reduction of 21.96% as compared with state-of-the-art technologies.

pdf bib
Improving Statistical Word Alignment with a Rule-Based Machine Translation System
Hua Wu | Haifeng Wang
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

Search
Co-authors