Chao Wang


2024

pdf bib
TeleChat: An Open-source Billingual Large Language Model
Zihan Wang | Liuxz2@chinatelecom.cn Liuxz2@chinatelecom.cn | Liusx14@chinatelecom.cn Liusx14@chinatelecom.cn | Yitong Yao | Huangyy121@chinatelecom.cn Huangyy121@chinatelecom.cn | Li Mengxiang | Zhongjiang He | Liyx25@chinatelecom.cn Liyx25@chinatelecom.cn | Pulw@chinatelecom.cn Pulw@chinatelecom.cn | Xuhn@chinatelecom.cn Xuhn@chinatelecom.cn | Chao Wang | Shuangyong Song
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)

In this paper, we present TeleChat, a collection of large language models (LLMs) with parameters of 7 billion and 12 billion. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, encompassing trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including general dialogue generation, language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves state-of-the-art performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat-7B and TeleChat-12B, along with code and a portion of our filtered high-quality pretraining data, to the public community.

pdf bib
Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs
Fengbin Zhu | Chao Wang | Fuli Feng | Zifeng Ren | Moxin Li | Tat-Seng Chua
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Table-text document (e.g., financial reports) understanding has attracted increasing attention in recent two years. TAT-DQA is a realistic setting for the understanding of visually-rich table-text documents, which involves answering associated questions requiring discrete reasoning. Most existing work relies on token-level semantics, falling short in the reasoning across document elements such as quantities and dates. To address this limitation, we propose a novel Doc2SoarGraph model that exploits element-level semantics and employs Semantic-oriented hierarchical Graph structures to capture the differences and correlations among different elements within the given document and question. Extensive experiments on the TAT-DQA dataset reveal that our model surpasses the state-of-the-art conventional method (i.e., MHST) and large language model (i.e., ChatGPT) by 17.73 and 6.49 points respectively in terms of Exact Match (EM) metric, demonstrating exceptional effectiveness.

2023

pdf bib
Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Tianshu Yu | Haoyu Gao | Ting-En Lin | Min Yang | Yuchuan Wu | Wentao Ma | Chao Wang | Fei Huang | Yongbin Li
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually tailored for one or two specific tasks, but fail to conquer a wide range of speech-text tasks. In addition, existing speech-text pre-training methods fail to explore the contextual information within a dialogue to enrich utterance representations. In this paper, we propose Speech-text Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model. Concretely, to consider the temporality of speech modality, we design a novel temporal position prediction task to capture the speech-text alignment. This pre-training task aims to predict the start and end time of each textual word in the corresponding speech waveform. In addition, to learn the characteristics of spoken dialogs, we generalize a response selection task from textual dialog pre-training to speech-text dialog pre-training scenarios. Experimental results on four different downstream speech-text tasks demonstrate the superiority of SPECTRA in learning speech-text alignment and multi-turn dialog context.

pdf bib
Causal Document-Grounded Dialogue Pre-training
Yingxiu Zhao | Bowen Yu | Bowen Li | Haiyang Yu | Jinyang Li | Chao Wang | Fei Huang | Yongbin Li | Nevin Zhang
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

The goal of document-grounded dialogue (DocGD) is to generate a response by anchoring the evidence in a supporting document in accordance with the dialogue context. This entails four causally interconnected variables. While task-specific pre-training has significantly enhanced performances on numerous downstream tasks, existing DocGD methods still rely on general pre-trained language models without a specifically tailored pre-training approach that explicitly captures the causal relationships. To address this, we present the first causally-complete dataset construction strategy for developing million-scale DocGD pre-training corpora. Additionally, we propose a causally-perturbed pre-training strategy to better capture causality by introducing perturbations on the variables and optimizing the overall causal effect. Experiments conducted on three benchmark datasets demonstrate that our causal pre-training yields substantial and consistent improvements in fully-supervised, low-resource, few-shot, and zero-shot settings.

pdf bib
CCL23-Eval 任务7赛道一系统报告:基于序列到序列模型的自动化文本纠错系统(System Report for CCL23-Eval Task 7 Track 1: Automated text error correction pipeline based on sequence-to-sequence models)
Shixuan Liu (刘世萱) | Xinzhang Liu (刘欣璋) | Yuyao Huang (黄钰瑶) | Chao Wang (王超) | Yongshuang Song (宋双永)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)

“本文介绍了本队伍在CCL-2023汉语学习者文本纠错评测大赛赛道一中提交的参赛系统。近年来,大规模的中文预训练模型在各种任务上表现出色,而不同的预训练模型在特定任务上也各有优势。然而,由于汉语学习者文本纠错任务存在语法错误复杂和纠错语料稀缺等特点,因此采用基于序列标记的预训练文本纠错模型来解决问题是自然的选择。我们的团队采用了序列到序列的纠错模型,并采取了两阶段训练策略,设计了一套基于序列到序列文本纠错的pipeline。首先,我们对训练集数据进行了清洗处理;在第一阶段训练中,我们在训练集上使用数据增强技术;在第二阶段,我们利用验证集进行微调,并最终采用多个模型投票集成的方式完成后处理。在实际的系统测评中,我们提交的结果在封闭任务排行榜上超出baseline模型17.01分(40.59->57.6)。”

2022

pdf bib
Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining
Chao Wang | Ehsan Nezhadarya | Tanmana Sadhu | Shengdong Zhang
Findings of the Association for Computational Linguistics: EMNLP 2022

Compositional image retrieval (CIR) is a challenging retrieval task, where the query is composed of a reference image and a modification text, and the target is another image reflecting the modification to the reference image. Due to the great success of the pre-trained vision-and-language model CLIP and its favorable applicability to large-scale retrieval tasks, we propose a CIR model HyCoLe-HNM with CLIP as the backbone. In HyCoLe-HNM, we follow the contrastive pre-training method of CLIP to perform cross-modal representation learning. On this basis, we propose a hybrid compositional learning mechanism, which includes both image compositional learning and text compositional learning. In hybrid compositional learning, we borrow a gated fusion mechanism from a question answering model to perform compositional fusion, and propose a heuristic negative mining method to filter negative samples. Privileged information in the form of image-related texts is utilized in cross-modal representation learning and hybrid compositional learning. Experimental results show that HyCoLe-HNM achieves state-of-the-art performance on three CIR datasets, namely FashionIQ, Fashion200K, and MIT-States.

pdf bib
基于GCN和门机制的汉语框架排歧方法(Chinese Frame Disambiguation Method Based on GCN and Gate Mechanism)
Yanan You (游亚男) | Ru Li (李茹) | Xuefeng Su (苏雪峰) | Zhichao Yan (闫智超) | Minshuai Sun (孙民帅) | Chao Wang (王超)
Proceedings of the 21st Chinese National Conference on Computational Linguistics

“汉语框架排歧旨在候选框架中给句子中的目标词选择一个符合其语义场景的框架。目前研究方法存在隐层向量的计算与目标词无关,并且忽略了句法结构信息对框架排歧的影响等缺陷。针对上述问题,使用GCN对句法结构信息进行建模;引入门机制过滤隐层向量中与目标词无关的噪声信息;并在此基础上,提出一种约束机制来约束模型的学习,改进向量表示。该模型在CFN、FN1.5和FN1.7数据集上优于当前最好模型,证明了方法的有效性。”

2021

pdf bib
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
Fengbin Zhu | Wenqiang Lei | Youcheng Huang | Chao Wang | Shuo Zhang | Jiancheng Lv | Fuli Feng | Tat-Seng Chua
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)

Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. We further propose a novel QA model termed TAGOP, which is capable of reasoning over both tables and text. It adopts sequence tagging to extract relevant cells from the table along with relevant spans from the text to infer their semantics, and then applies symbolic reasoning over them with a set of aggregation operators to arrive at the final answer. TAGOP achieves 58.0% inF1, which is an 11.1% absolute increase over the previous best baseline model, according to our experiments on TAT-QA. But this result still lags far behind performance of expert human, i.e.90.8% in F1. It is demonstrated that our TAT-QA is very challenging and can serve as a benchmark for training and testing powerful QA models that address hybrid form data.

pdf bib
An Emotional Comfort Framework for Improving User Satisfaction in E-Commerce Customer Service Chatbots
Shuangyong Song | Chao Wang | Haiqing Chen | Huan Chen
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

E-commerce has grown substantially over the last several years, and chatbots for intelligent customer service are concurrently drawing attention. We presented AliMe Assist, a Chinese intelligent assistant designed for creating an innovative online shopping experience in E-commerce. Based on question answering (QA), AliMe Assist offers assistance service, customer service, and chatting service. According to the survey of user studies and the real online testing, emotional comfort of customers’ negative emotions, which make up more than 5% of whole number of customer visits on AliMe, is a key point for providing considerate service. In this paper, we propose a framework to obtain proper answer to customers’ emotional questions. The framework takes emotion classification model as a core, and final answer selection is based on topic classification and text matching. Our experiments on real online systems show that the framework is very promising.

pdf bib
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation
Chao Wang | Judith Gaspers | Thi Ngoc Quynh Do | Hui Jiang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

2020

pdf bib
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling
Xu Cao | Deyi Xiong | Chongyang Shi | Chao Wang | Yao Meng | Changjian Hu
Proceedings of the 28th International Conference on Computational Linguistics

Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding. However, many joint models still suffer from the robustness problem, especially on noisy inputs or rare/unseen events. To address this issue, we propose a Joint Adversarial Training (JAT) model to improve the robustness of joint intent detection and slot filling, which consists of two parts: (1) automatically generating joint adversarial examples to attack the joint model, and (2) training the model to defend against the joint adversarial examples so as to robustify the model on small perturbations. As the generated joint adversarial examples have different impacts on the intent detection and slot filling loss, we further propose a Balanced Joint Adversarial Training (BJAT) model that applies a balance factor as a regularization term to the final loss function, which yields a stable training procedure. Extensive experiments and analyses on the lightweight models show that our proposed methods achieve significantly higher scores and substantially improve the robustness of both intent detection and slot filling. In addition, the combination of our BJAT with BERT-large achieves state-of-the-art results on two datasets.

pdf bib
Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
Hanchu Zhang | Leonhard Hennig | Christoph Alt | Changjian Hu | Yao Meng | Chao Wang
Proceedings of the 3rd Workshop on e-Commerce and NLP

In this work, we introduce a bootstrapped, iterative NER model that integrates a PU learning algorithm for recognizing named entities in a low-resource setting. Our approach combines dictionary-based labeling with syntactically-informed label expansion to efficiently enrich the seed dictionaries. Experimental results on a dataset of manually annotated e-commerce product descriptions demonstrate the effectiveness of the proposed framework.

2019

pdf bib
Multimodal and Multi-view Models for Emotion Recognition
Gustavo Aguilar | Viktor Rozgic | Weiran Wang | Chao Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities are available in training and evaluation. However, in practice, this is not always the case; getting ASR output may represent a bottleneck in a deployment pipeline due to computational complexity or privacy-related constraints. To address this challenge, we study the problem of efficiently combining acoustic and lexical modalities during training while still providing a deployable acoustic model that does not require lexical inputs. We first experiment with multimodal models and two attention mechanisms to assess the extent of the benefits that lexical information can provide. Then, we frame the task as a multi-view learning problem to induce semantic information from a multimodal model into our acoustic-only network using a contrastive loss function. Our multimodal model outperforms the previous state of the art on the USC-IEMOCAP dataset reported on lexical and acoustic information. Additionally, our multi-view-trained acoustic network significantly surpasses models that have been exclusively trained with acoustic features.

pdf bib
Explicit Utilization of General Knowledge in Machine Reading Comprehension
Chao Wang | Hui Jiang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. Based on the data enrichment method, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. When only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise.

pdf bib
The Lower The Simpler: Simplifying Hierarchical Recurrent Models
Chao Wang | Hui Jiang
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

To improve the training efficiency of hierarchical recurrent models without compromising their performance, we propose a strategy named as “the lower the simpler”, which is to simplify the baseline models by making the lower layers simpler than the upper layers. We carry out this strategy to simplify two typical hierarchical recurrent models, namely Hierarchical Recurrent Encoder-Decoder (HRED) and R-NET, whose basic building block is GRU. Specifically, we propose Scalar Gated Unit (SGU), which is a simplified variant of GRU, and use it to replace the GRUs at the middle layers of HRED and R-NET. Besides, we also use Fixed-size Ordinally-Forgetting Encoding (FOFE), which is an efficient encoding method without any trainable parameter, to replace the GRUs at the bottom layers of HRED and R-NET. The experimental results show that the simplified HRED and the simplified R-NET contain significantly less trainable parameters, consume significantly less training time, and achieve slightly better performance than their baseline models.

pdf bib
Improving Back-Translation with Uncertainty-based Confidence Estimation
Shuo Wang | Yang Liu | Chao Wang | Huanbo Luan | Maosong Sun
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translation tasks show that uncertainty-based confidence estimation significantly improves the performance of back-translation.

2011

pdf bib
A Unified and Discriminative Soft Syntactic Constraint Model for Hierarchical Phrase-based Translation
Lemao Liu | Tiejun Zhao | Chao Wang | Hailong Cao
Proceedings of Machine Translation Summit XIII: Papers

2008

pdf bib
A Multimodal Home Entertainment Interface via a Mobile Device
Alexander Gruenstein | Bo-June Paul Hsu | James Glass | Stephanie Seneff | Lee Hetherington | Scott Cyphers | Ibrahim Badr | Chao Wang | Sean Liu
Proceedings of the ACL-08: HLT Workshop on Mobile Language Processing

2007

pdf bib
Automatic Assessment of Student Translations for Foreign Language Tutoring
Chao Wang | Stephanie Seneff
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference

pdf bib
Spoken Dialogue Systems for Language Learning
Stephanie Seneff | Chao Wang | Chih-yu Chao
Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT)

pdf bib
Chinese Syntactic Reordering for Statistical Machine Translation
Chao Wang | Michael Collins | Philipp Koehn
Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)

2006

pdf bib
Combining Linguistic and Statistical Methods for Bi-directional English Chinese Translation in the Flight Domain
Stephanie Seneff | Chao Wang | John Lee
Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers

In this paper, we discuss techniques to combine an interlingua translation framework with phrase-based statistical methods, for translation from Chinese into English. Our goal is to achieve high-quality translation, suitable for use in language tutoring applications. We explore these ideas in the context of a flight domain, for which we have a large corpus of English queries, obtained from users interacting with a dialogue system. Our techniques exploit a pre-existing English-to-Chinese translation system to automatically produce a synthetic bilingual corpus. Several experiments were conducted combining linguistic and statistical methods, and manual evaluation was conducted for a set of 460 Chinese sentences. The best performance achieved an “adequate” or better analysis (3 or above rating) on nearly 94% of the 409 parsable subset. Using a Rover scheme to combine four systems resulted in an “adequate or better” rating for 88% of all the utterances.

2005

pdf bib
Automatic Induction of Language Model Data for A Spoken Dialogue System
Grace Chung | Stephanie Seneff | Chao Wang
Proceedings of the 6th SIGdial Workshop on Discourse and Dialogue

2004

pdf bib
Analysis and Processing of Lecture Audio Data: Preliminary Investigations
James Glass | Timothy J. Hazen | Lee Hetherington | Chao Wang
Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004

2003

pdf bib
Automatic Acquisition of Names Using Speak and Spell Mode in Spoken Dialogue Systems
Grace Chung | Stephanie Seneff | Chao Wang
Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics

Search