Linfeng Song


pdf bib
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
Xiangci Li | Linfeng Song | Lifeng Jin | Haitao Mi | Jessica Ouyang | Dong Yu
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Knowledge-based, open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. Many types and sources of knowledge have previously been shown to be useful as support knowledge. Even in the era of large language models, response generation grounded in knowledge retrieved from additional up-to-date sources remains a practically important approach. While prior work using single-source knowledge has shown a clear positive correlation between the performances of knowledge selection and response generation, there are no existing multi-source datasets for evaluating support knowledge retrieval. Further, prior work has assumed that the knowledge sources available at test time are the same as during training. This unrealistic assumption unnecessarily handicaps models, as new knowledge sources can become available after a model is trained. In this paper, we present a high-quality benchmark named multi-source Wizard of Wikipedia (Ms.WoW) for evaluating multi-source dialogue knowledge selection and response generation. Unlike existing datasets, it contains clean support knowledge, grounded at the utterance level and partitioned into multiple knowledge sources. We further propose a new challenge, dialogue knowledge plug-and-play, which aims to test an already trained dialogue model on using new support knowledge from previously unseen sources in a zero-shot fashion.

pdf bib
Inconsistent dialogue responses and how to recover from them
Mian Zhang | Lifeng Jin | Linfeng Song | Haitao Mi | Dong Yu
Findings of the Association for Computational Linguistics: EACL 2024

One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself, which has been shown a difficult problem. In this work, we study methods to assess and bolster utterance consistency of chat systems. A dataset is first developed for studying the inconsistencies, where inconsistent dialogue responses, explanations of the inconsistencies, and recovery utterances are authored by annotators. This covers the life span of inconsistencies, namely introduction, understanding, and resolution. Building on this, we introduce a set of tasks centered on dialogue consistency, specifically focused on its detection and resolution. Our experimental findings indicate that our dataset significantly helps the progress in identifying and resolving conversational inconsistencies, and current popular large language models like ChatGPT which are good at resolving inconsistencies however still struggle with detection.


pdf bib
Friend-training: Learning from Models of Different but Related Tasks
Mian Zhang | Lifeng Jin | Linfeng Song | Haitao Mi | Xiabing Zhou | Dong Yu
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architectures, and training processes. However, many tasks in natural language processing are about different but related aspects of language, and models trained for one task can be great teachers for other related tasks. In this work, we propose friend-training, a cross-task self-training framework, where models trained to do different tasks are used in an iterative training, pseudo-labeling, and retraining process to help each other for better selection of pseudo-labels. With two dialogue understanding tasks, conversational semantic role labeling and dialogue rewriting, chosen for a case study, we show that the models trained with the friend-training framework achieve the best performance compared to strong baselines.

pdf bib
Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training
Sai Ashish Somayajula | Lifeng Jin | Linfeng Song | Haitao Mi | Dong Yu
Findings of the Association for Computational Linguistics: ACL 2023

Training a large language model in low-resource settings is challenging since they are susceptible to overfitting with limited generalization abilities. Previous work addresses this issue by approaches such as tunable parameters reduction or data augmentation. However, they either limit the trained models’ expressiveness or rely on task-independent knowledge. In this paper, we propose the Bi-level Finetuning with Task-dependent Similarity Structure framework where all parameters, including the embeddings for unseen tokens, are finetuned with task-dependent information from the training data only. In this framework, a task-dependent similarity structure is learned in a data-driven fashion, which in turn is used to compose soft embeddings from conventional embeddings to be used in training to update all parameters. In order to learn the similarity structure and model parameters, we propose a bi-level optimization algorithm with two stages—search and finetune—to ensure successful learning. Results of experiments on several classification datasets in low-resource scenarios demonstrate that models trained with our method outperform strong baselines. Ablation experiments further support the effectiveness of different components in our framework. Code is available at

pdf bib
Domain Adaptation for Conversational Query Production with the RAG Model Feedback
Ante Wang | Linfeng Song | Ge Xu | Jinsong Su
Findings of the Association for Computational Linguistics: EMNLP 2023

Conversational query production is an emerging fundamental task for the dialogue system, where search queries are generated to explore the vast and continually updating knowledge from a search engine. To accelerate this line of research, previous studies have released several datasets with human-annotated search queries. However, the limited annotations still can not cover conversations of various domains. To solve this challenge, we propose a novel domain adaptation framework. It is inspired by a weakly supervised learning algorithm from previous work that guides a model using reinforcement learning with BM25 scores as feedback. Though effective, it is fragile facing noisy content on webpages from a commercial search engine and variance in conversations because of ignoring deep semantic information of dialogue contexts. Thus, we improve the algorithm by taking the advance of retrieval-augmented generation (RAG) and exploring several practical techniques such as knowledge distillation for stable training. We conduct experiments in multiple settings across different languages. Guided by the RAG model feedback, our model is more robust and performs significantly better especially in a more challenging setting over strong baselines.

pdf bib
OpenFact: Factuality Enhanced Open Knowledge Extraction
Linfeng Song | Ante Wang | Xiaoman Pan | Hongming Zhang | Dian Yu | Lifeng Jin | Haitao Mi | Jinsong Su | Yue Zhang | Dong Yu
Transactions of the Association for Computational Linguistics, Volume 11

We focus on the factuality property during the extraction of an OpenIE corpus named OpenFact, which contains more than 12 million high-quality knowledge triplets. We break down the factuality property into two important aspects—expressiveness and groundedness—and we propose a comprehensive framework to handle both aspects. To enhance expressiveness, we formulate each knowledge piece in OpenFact based on a semantic frame. We also design templates, extra constraints, and adopt human efforts so that most OpenFact triplets contain enough details. For groundedness, we require the main arguments of each triplet to contain linked Wikidata1 entities. A human evaluation suggests that the OpenFact triplets are much more accurate and contain denser information compared to OPIEC-Linked (Gashteovski et al., 2019), one recent high-quality OpenIE corpus grounded to Wikidata. Further experiments on knowledge base completion and knowledge base question answering show the effectiveness of OpenFact over OPIEC-Linked as supplementary knowledge to Wikidata as the major KG.

pdf bib
SafeConv: Explaining and Correcting Conversational Unsafe Behavior
Mian Zhang | Lifeng Jin | Linfeng Song | Haitao Mi | Wenliang Chen | Dong Yu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

One of the main challenges open-domain end-to-end dialogue systems, or chatbots, face is the prevalence of unsafe behavior, such as toxic languages and harmful suggestions. However, existing dialogue datasets do not provide enough annotation to explain and correct such unsafe behavior. In this work, we construct a new dataset called SafeConv for the research of conversational safety: (1) Besides the utterance-level safety labels, SafeConv also provides unsafe spans in an utterance, information able to indicate which words contribute to the detected unsafe behavior; (2) SafeConv provides safe alternative responses to continue the conversation when unsafe behavior detected, guiding the conversation to a gentle trajectory. By virtue of the comprehensive annotation of SafeConv, we benchmark three powerful models for the mitigation of conversational unsafe behavior, including a checker to detect unsafe utterances, a tagger to extract unsafe spans, and a rewriter to convert an unsafe response to a safe version. Moreover, we explore the huge benefits brought by combining the models for explaining the emergence of unsafe behavior and detoxifying chatbots. Experiments show that the detected unsafe behavior could be well explained with unsafe spans and popular chatbots could be detoxified by a huge extent. The dataset is available at

pdf bib
A Survey on Zero Pronoun Translation
Longyue Wang | Siyou Liu | Mingzhou Xu | Linfeng Song | Shuming Shi | Zhaopeng Tu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Zero pronouns (ZPs) are frequently omitted in pro-drop languages (e.g. Chinese, Hungarian, and Hindi), but should be recalled in non-pro-drop languages (e.g. English). This phenomenon has been studied extensively in machine translation (MT), as it poses a significant challenge for MT systems due to the difficulty in determining the correct antecedent for the pronoun. This survey paper highlights the major works that have been undertaken in zero pronoun translation (ZPT) after the neural revolution so that researchers can recognize the current state and future directions of this field. We provide an organization of the literature based on evolution, dataset, method, and evaluation. In addition, we compare and analyze competing models and evaluation metrics on different benchmarks. We uncover a number of insightful findings such as: 1) ZPT is in line with the development trend of large language model; 2) data limitation causes learning bias in languages and domains; 3) performance improvements are often reported on single benchmarks, but advanced methods are still far from real-world use; 4) general-purpose metrics are not reliable on nuances and complexities of ZPT, emphasizing the necessity of targeted metrics; 5) apart from commonly-cited errors, ZPs will cause risks of gender bias.


pdf bib
Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution
Irene Li | Linfeng Song | Kun Xu | Dong Yu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Coreference resolution over semantic graphs like AMRs aims to group the graph nodes that represent the same entity. This is a crucial step for making document-level formal semantic representations. With annotated data on AMR coreference resolution, deep learning approaches have recently shown great potential for this task, yet they are usually data hunger and annotations are costly. We propose a general pretraining method using variational graph autoencoder (VGAE) for AMR coreference resolution, which can leverage any general AMR corpus and even automatically parsed AMR data. Experiments on benchmarks show that the pretraining approach achieves performance gains of up to 6% absolute F1 points. Moreover, our model significantly improves on the previous state-of-the-art model by up to 11% F1.

pdf bib
A Multi-Level Optimization Framework for End-to-End Text Augmentation
Sai Ashish Somayajula | Linfeng Song | Pengtao Xie
Transactions of the Association for Computational Linguistics, Volume 10

Text augmentation is an effective technique in alleviating overfitting in NLP tasks. In existing methods, text augmentation and downstream tasks are mostly performed separately. As a result, the augmented texts may not be optimal to train the downstream model. To address this problem, we propose a three-level optimization framework to perform text augmentation and the downstream task end-to- end. The augmentation model is trained in a way tailored to the downstream task. Our framework consists of three learning stages. A text summarization model is trained to perform data augmentation at the first stage. Each summarization example is associated with a weight to account for its domain difference with the text classification data. At the second stage, we use the model trained at the first stage to perform text augmentation and train a text classification model on the augmented texts. At the third stage, we evaluate the text classification model trained at the second stage and update weights of summarization examples by minimizing the validation loss. These three stages are performed end-to-end. We evaluate our method on several text classification datasets where the results demonstrate the effectiveness of our method. Code is available at

pdf bib
Getting the Most out of Simile Recognition
Xiaoyue Wang | Linfeng Song | Xin Liu | Chulun Zhou | Hualin Zeng | Jinsong Su
Findings of the Association for Computational Linguistics: EMNLP 2022

Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the corresponding objects (i.e., tenors and vehicles).Recent work ignores features other than surface strings and suffers from the data hunger issue.We explore expressive features for this task to help achieve more effective data utilization.In particular, we study two types of features: 1) input-side features that include POS tags, dependency trees and word definitions, and 2) decoding features that capture the interdependence among various decoding decisions.We further construct a model named HGSR, which merges the input-side features as a heterogeneous graph and leverages decoding features via distillation.Experiments show that HGSR significantly outperforms the current state-of-the-art systems and carefully designed baselines, verifying the effectiveness of introduced features. We will release our code upon paper acceptance.

pdf bib
Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup
Peng Shi | Linfeng Song | Lifeng Jin | Haitao Mi | He Bai | Jimmy Lin | Dong Yu
Findings of the Association for Computational Linguistics: EMNLP 2022

We focus on the cross-lingual Text-to-SQL semantic parsing task,where the parsers are expected to generate SQL for non-English utterances based on English database schemas.Intuitively, English translation as side information is an effective way to bridge the language gap,but noise introduced by the translation system may affect parser effectiveness.In this work, we propose a Representation Mixup Framework (Rex) for effectively exploiting translations in the cross-lingual Text-to-SQL task.Particularly, it uses a general encoding layer, a transition layer, and a target-centric layer to properly guide the information flow of the English translation.Experimental results on CSpider and VSpider show that our framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance.

pdf bib
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
Qi Liu | Zihuiwen Ye | Tao Yu | Linfeng Song | Phil Blunsom
Findings of the Association for Computational Linguistics: EMNLP 2022

The task of context-dependent text-to-SQL aims to convert multi-turn user utterances to formal SQL queries. This is a challenging task due to both the scarcity of training data from which to learn complex contextual dependencies and to generalize to unseen databases. In this paper we explore augmenting the training datasets using self-play, which leverages contextual information to synthesize new interactions to adapt the model to new databases. We first design a SQL-to-text model conditioned on a sampled goal query, which represents a user’s intent, that then converses with a text-to-SQL semantic parser to generate new interactions. We then filter the synthesized interactions and retrain the models with the augmented data. We find that self-play improves the accuracy of a strong baseline on SParC and CoSQL, two widely used cross-domain text-to-SQL datasets. Our analysis shows that self-play simulates various conversational thematic relations, enhances cross-domain generalization and improves beam-search.

pdf bib
Learning a Grammar Inducer from Massive Uncurated Instructional Videos
Songyang Zhang | Linfeng Song | Lifeng Jin | Haitao Mi | Kun Xu | Dong Yu | Jiebo Luo
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Video-aided grammar induction aims to leverage video information for finding more accurate syntactic grammars for accompanying text. While previous work focuses on building systems for inducing grammars on text that are well-aligned with video content, we investigate the scenario, in which text and video are only in loose correspondence. Such data can be found in abundance online, and the weak correspondence is similar to the indeterminacy problem studied in language acquisition. Furthermore, we build a new model that can better learn video-span correlation without manually designed features adopted by previous work. Experiments show that our model trained only on large-scale YouTube data with no text-video alignment reports strong and robust performances across three unseen datasets, despite domain shift and noisy label issues. Furthermore our model yields higher F1 scores than the previous state-of-the-art systems trained on in-domain data.

pdf bib
Cross-domain Generalization for AMR Parsing
Xuefeng Bai | Sen Yang | Leyang Cui | Linfeng Song | Yue Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Abstract Meaning Representation (AMR) parsing aims to predict an AMR graph from textual input. Recently, there has been notable growth in AMR parsing performance. However, most existing work focuses on improving the performance in the specific domain, ignoring the potential domain dependence of AMR parsing systems. To address this, we extensively evaluate five representative AMR parsers on five domains and analyze challenges to cross-domain AMR parsing. We observe that challenges to cross-domain AMR parsing mainly arise from the distribution shift of words and AMR concepts. Based on our observation, we investigate two approaches to reduce the domain distribution divergence of text and AMR features, respectively. Experimental results on two out-of-domain test sets show the superiority of our method.

pdf bib
GuoFeng: A Benchmark for Zero Pronoun Recovery and Translation
Mingzhou Xu | Longyue Wang | Derek F. Wong | Hongye Liu | Linfeng Song | Lidia S. Chao | Shuming Shi | Zhaopeng Tu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

The phenomenon of zero pronoun (ZP) has attracted increasing interest in the machine translation (MT) community due to its importance and difficulty. However, previous studies generally evaluate the quality of translating ZPs with BLEU scores on MT testsets, which is not expressive or sensitive enough for accurate assessment. To bridge the data and evaluation gaps, we propose a benchmark testset for target evaluation on Chinese-English ZP translation. The human-annotated testset covers five challenging genres, which reveal different characteristics of ZPs for comprehensive evaluation. We systematically revisit eight advanced models on ZP translation and identify current challenges for future exploration. We release data, code, models and annotation guidelines, which we hope can significantly promote research in this field (

pdf bib
Semantic-based Pre-training for Dialogue Understanding
Xuefeng Bai | Linfeng Song | Yue Zhang
Proceedings of the 29th International Conference on Computational Linguistics

Pre-trained language models have made great progress on dialogue tasks. However, these models are typically trained on surface dialogue text, thus are proven to be weak in understanding the main semantic meaning of a dialogue context. We investigate Abstract Meaning Representation (AMR) as explicit semantic knowledge for pre-training models to capture the core semantic information in dialogues during pre-training. In particular, we propose a semantic-based pre-training framework that extends the standard pre-training framework (Devlin et al.,2019) by three tasks for learning 1) core semantic units, 2) semantic relations and 3) the overall semantic representation according to AMR graphs. Experiments on the understanding of both chit-chats and task-oriented dialogues show the superiority of our model. To our knowledge, we are the first to leverage a deep semantic representation for dialogue pre-training.


pdf bib
Video-aided Unsupervised Grammar Induction
Songyang Zhang | Linfeng Song | Lifeng Jin | Kun Xu | Dong Yu | Jiebo Luo
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video. Existing methods of multi-modal grammar induction focus on grammar induction from text-image pairs, with promising results showing that the information from static images is useful in induction. However, videos provide even richer information, including not only static objects but also actions and state changes useful for inducing verb phrases. In this paper, we explore rich features (e.g. action, object, scene, audio, face, OCR and speech) from videos, taking the recent Compound PCFG model as the baseline. We further propose a Multi-Modal Compound PCFG model (MMC-PCFG) to effectively aggregate these rich features from different modalities. Our proposed MMC-PCFG is trained end-to-end and outperforms each individual modality and previous state-of-the-art systems on three benchmarks, i.e. DiDeMo, YouCook2 and MSRVTT, confirming the effectiveness of leveraging video information for unsupervised grammar induction.

pdf bib
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
Jie Hao | Linfeng Song | Liwei Wang | Kun Xu | Zhaopeng Tu | Dong Yu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances drop dramatically when testing on a different dataset. We address this robustness issue by proposing a novel sequence-tagging-based model so that the search space is significantly reduced, yet the core of this task is still well covered. As a common issue of most tagging models for text generation, the model’s outputs may lack fluency. To alleviate this issue, we inject the loss signal from BLEU or GPT-2 under a REINFORCE framework. Experiments show huge improvements of our model over the current state-of-the-art systems when transferring to another dataset.

pdf bib
Instance-adaptive training with noise-robust losses against noisy labels
Lifeng Jin | Linfeng Song | Kun Xu | Dong Yu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In order to alleviate the huge demand for annotated datasets for different tasks, many recent natural language processing datasets have adopted automated pipelines for fast-tracking usable data. However, model training with such datasets poses a challenge because popular optimization objectives are not robust to label noise induced in the annotation generation process. Several noise-robust losses have been proposed and evaluated on tasks in computer vision, but they generally use a single dataset-wise hyperparamter to control the strength of noise resistance. This work proposes novel instance-adaptive training frameworks to change single dataset-wise hyperparameters of noise resistance in such losses to be instance-wise. Such instance-wise noise resistance hyperparameters are predicted by special instance-level label quality predictors, which are trained along with the main classification models. Experiments on noisy and corrupted NLP datasets show that proposed instance-adaptive training frameworks help increase the noise-robustness provided by such losses, promoting the use of the frameworks and associated losses in NLP models trained with noisy data.

pdf bib
End-to-End AMR Coreference Resolution
Qiankun Fu | Linfeng Song | Wenyu Du | Yue Zhang
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)

Although parsing to Abstract Meaning Representation (AMR) has become very popular and AMR has been shown effective on the many sentence-level downstream tasks, little work has studied how to generate AMRs that can represent multi-sentence information. We introduce the first end-to-end AMR coreference resolution model in order to build multi-sentence AMRs. Compared with the previous pipeline and rule-based approaches, our model alleviates error propagation and it is more robust for both in-domain and out-domain situations. Besides, the document-level AMRs obtained by our model can significantly improve over the AMRs generated by a rule-based method (Liu et al., 2015) on text summarization.

pdf bib
Semantic Representation for Dialogue Modeling
Xuefeng Bai | Yulong Chen | Linfeng Song | Yue Zhang
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)

Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR) to help dialogue modeling. Compared with the textual input, AMR explicitly provides core semantic knowledge and reduces data sparsity. We develop an algorithm to construct dialogue-level AMR graphs from sentence-level AMRs and explore two ways to incorporate AMRs into dialogue systems. Experimental results on both dialogue understanding and response generation tasks show the superiority of our model. To our knowledge, we are the first to leverage a formal semantic representation into neural dialogue modeling.

pdf bib
Domain-Adaptive Pretraining Methods for Dialogue Understanding
Han Wu | Kun Xu | Linfeng Song | Lifeng Jin | Haisong Zhang | Linqi Song
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)

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream tasks. In particular, three objectives, including a novel objective focusing on modeling predicate-argument relations, are evaluated on two challenging dialogue understanding tasks. Experimental results demonstrate that domain-adaptive pretraining with proper objectives can significantly improve the performance of a strong baseline on these tasks, achieving the new state-of-the-art performances.

pdf bib
TexSmart: A System for Enhanced Natural Language Understanding
Lemao Liu | Haisong Zhang | Haiyun Jiang | Yangming Li | Enbo Zhao | Kun Xu | Linfeng Song | Suncong Zheng | Botong Zhou | Dick Zhu | Xiao Feng | Tao Chen | Tao Yang | Dong Yu | Feng Zhang | ZhanHui Kang | Shuming Shi
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations

This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features. First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types. Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications. The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human annotation efforts.

pdf bib
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs
Pei Ke | Haozhe Ji | Yu Ran | Xin Cui | Liwei Wang | Linfeng Song | Xiaoyan Zhu | Minlie Huang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


pdf bib
ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT
Linfeng Song | Kun Xu | Yue Zhang | Jianshu Chen | Dong Yu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Zero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively. We propose to better explore their interaction by solving both tasks together, while the previous work treats them separately. For zero pronoun resolution, we study this task in a more realistic setting, where no parsing trees or only automatic trees are available, while most previous work assumes gold trees. Experiments on two benchmarks show that joint modeling significantly outperforms our baseline that already beats the previous state of the arts.

pdf bib
Structural Information Preserving for Graph-to-Text Generation
Linfeng Song | Ante Wang | Jinsong Su | Yue Zhang | Kun Xu | Yubin Ge | Dong Yu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs. We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information. In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a. views) of input graphs. The losses are then back-propagated to better calibrate our model via multi-task training. Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline.

pdf bib
Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer
Hongyu Gong | Linfeng Song | Suma Bhat
Proceedings of the 13th International Conference on Natural Language Generation

Text style transfer aims to change an input sentence to an output sentence by changing its text style while preserving the content. Previous efforts on unsupervised text style transfer only use the surface features of words and sentences. As a result, the transferred sentences may either have inaccurate or missing information compared to the inputs. We address this issue by explicitly enriching the inputs via syntactic and semantic structures, from which richer features are then extracted to better capture the original information. Experiments on two text-style-transfer tasks show that our approach improves the content preservation of a strong unsupervised baseline model thereby demonstrating improved transfer performance.

pdf bib
Online Back-Parsing for AMR-to-Text Generation
Xuefeng Bai | Linfeng Song | Yue Zhang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

AMR-to-text generation aims to recover a text containing the same meaning as an input AMR graph. Current research develops increasingly powerful graph encoders to better represent AMR graphs, with decoders based on standard language modeling being used to generate outputs. We propose a decoder that back predicts projected AMR graphs on the target sentence during text generation. As the result, our outputs can better preserve the input meaning than standard decoders. Experiments on two AMR benchmarks show the superiority of our model over the previous state-of-the-art system based on graph Transformer.

pdf bib
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter
Kun Xu | Haochen Tan | Linfeng Song | Han Wu | Haisong Zhang | Linqi Song | Dong Yu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting ride of the noises is essential to improve its performance. Existing attentive models attend to all words without prior focus, which results in inaccurate concentration on some dispensable words. In this paper, we propose to use semantic role labeling (SRL), which highlights the core semantic information of who did what to whom, to provide additional guidance for the rewriter model. Experiments show that this information significantly improves a RoBERTa-based model that already outperforms previous state-of-the-art systems.


pdf bib
Semantic Neural Machine Translation Using AMR
Linfeng Song | Daniel Gildea | Yue Zhang | Zhiguo Wang | Jinsong Su
Transactions of the Association for Computational Linguistics, Volume 7

It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.

pdf bib
Multi-Granular Text Encoding for Self-Explaining Categorization
Zhiguo Wang | Yue Zhang | Mo Yu | Wei Zhang | Lin Pan | Linfeng Song | Kun Xu | Yousef El-Kurdi
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence. A popular type of evidence is sub-sequences extracted from the input text which are sufficient for the classifier to make the prediction. In this work, we define multi-granular ngrams as basic units for explanation, and organize all ngrams into a hierarchical structure, so that shorter ngrams can be reused while computing longer ngrams. We leverage the tree-structured LSTM to learn a context-independent representation for each unit via parameter sharing. Experiments on medical disease classification show that our model is more accurate, efficient and compact than the BiLSTM and CNN baselines. More importantly, our model can extract intuitive multi-granular evidence to support its predictions.

pdf bib
Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis
Jialong Tang | Ziyao Lu | Jinsong Su | Yubin Ge | Linfeng Song | Le Sun | Jiebo Luo
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect. However, such a mechanism tends to excessively focus on a few frequent words with sentiment polarities, while ignoring infrequent ones. In this paper, we propose a progressive self-supervised attention learning approach for neural ASC models, which automatically mines useful attention supervision information from a training corpus to refine attention mechanisms. Specifically, we iteratively conduct sentiment predictions on all training instances. Particularly, at each iteration, the context word with the maximum attention weight is extracted as the one with active/misleading influence on the correct/incorrect prediction of every instance, and then the word itself is masked for subsequent iterations. Finally, we augment the conventional training objective with a regularization term, which enables ASC models to continue equally focusing on the extracted active context words while decreasing weights of those misleading ones. Experimental results on multiple datasets show that our proposed approach yields better attention mechanisms, leading to substantial improvements over the two state-of-the-art neural ASC models. Source code and trained models are available at

pdf bib
SemBleu: A Robust Metric for AMR Parsing Evaluation
Linfeng Song | Daniel Gildea
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Evaluating AMR parsing accuracy involves comparing pairs of AMR graphs. The major evaluation metric, SMATCH (Cai and Knight, 2013), searches for one-to-one mappings between the nodes of two AMRs with a greedy hill-climbing algorithm, which leads to search errors. We propose SEMBLEU, a robust metric that extends BLEU (Papineni et al., 2002) to AMRs. It does not suffer from search errors and considers non-local correspondences in addition to local ones. SEMBLEU is fully content-driven and punishes situations where a system’s output does not preserve most information from the input. Preliminary experiments on both sentence and corpus levels show that SEMBLEU has slightly higher consistency with human judgments than SMATCH. Our code is available at

pdf bib
Leveraging Dependency Forest for Neural Medical Relation Extraction
Linfeng Song | Yue Zhang | Daniel Gildea | Mo Yu | Zhiguo Wang | Jinsong Su
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Medical relation extraction discovers relations between entity mentions in text, such as research articles. For this task, dependency syntax has been recognized as a crucial source of features. Yet in the medical domain, 1-best parse trees suffer from relatively low accuracies, diminishing their usefulness. We investigate a method to alleviate this problem by utilizing dependency forests. Forests contain more than one possible decisions and therefore have higher recall but more noise compared with 1-best outputs. A graph neural network is used to represent the forests, automatically distinguishing the useful syntactic information from parsing noise. Results on two benchmarks show that our method outperforms the standard tree-based methods, giving the state-of-the-art results in the literature.


pdf bib
N-ary Relation Extraction using Graph-State LSTM
Linfeng Song | Yue Zhang | Zhiguo Wang | Daniel Gildea
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Cross-sentence n-ary relation extraction detects relations among n entities across multiple sentences. Typical methods formulate an input as a document graph, integrating various intra-sentential and inter-sentential dependencies. The current state-of-the-art method splits the input graph into two DAGs, adopting a DAG-structured LSTM for each. Though being able to model rich linguistic knowledge by leveraging graph edges, important information can be lost in the splitting procedure. We propose a graph-state LSTM model, which uses a parallel state to model each word, recurrently enriching state values via message passing. Compared with DAG LSTMs, our graph LSTM keeps the original graph structure, and speeds up computation by allowing more parallelization. On a standard benchmark, our model shows the best result in the literature.

pdf bib
Sentence-State LSTM for Text Representation
Yue Zhang | Qi Liu | Linfeng Song
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, which consists of a parallel state for each word. Recurrent steps are used to perform local and global information exchange between words simultaneously, rather than incremental reading of a sequence of words. Results on various classification and sequence labelling benchmarks show that the proposed model has strong representation power, giving highly competitive performances compared to stacked BiLSTM models with similar parameter numbers.

pdf bib
A Graph-to-Sequence Model for AMR-to-Text Generation
Linfeng Song | Yue Zhang | Zhiguo Wang | Daniel Gildea
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. Although being able to model non-local semantic information, a sequence LSTM can lose information from the AMR graph structure, and thus facing challenges with large-graphs, which result in long sequences. We introduce a neural graph-to-sequence model, using a novel LSTM structure for directly encoding graph-level semantics. On a standard benchmark, our model shows superior results to existing methods in the literature.

pdf bib
Sequence-to-sequence Models for Cache Transition Systems
Xiaochang Peng | Linfeng Song | Daniel Gildea | Giorgio Satta
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we present a sequence-to-sequence based approach for mapping natural language sentences to AMR semantic graphs. We transform the sequence to graph mapping problem to a word sequence to transition action sequence problem using a special transition system called a cache transition system. To address the sparsity issue of neural AMR parsing, we feed feature embeddings from the transition state to provide relevant local information for each decoder state. We present a monotonic hard attention model for the transition framework to handle the strictly left-to-right alignment between each transition state and the current buffer input focus. We evaluate our neural transition model on the AMR parsing task, and our parser outperforms other sequence-to-sequence approaches and achieves competitive results in comparison with the best-performing models.

pdf bib
Leveraging Context Information for Natural Question Generation
Linfeng Song | Zhiguo Wang | Wael Hamza | Yue Zhang | Daniel Gildea
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

The task of natural question generation is to generate a corresponding question given the input passage (fact) and answer. It is useful for enlarging the training set of QA systems. Previous work has adopted sequence-to-sequence models that take a passage with an additional bit to indicate answer position as input. However, they do not explicitly model the information between answer and other context within the passage. We propose a model that matches the answer with the passage before generating the question. Experiments show that our model outperforms the existing state of the art using rich features.

pdf bib
Neural Transition-based Syntactic Linearization
Linfeng Song | Yue Zhang | Daniel Gildea
Proceedings of the 11th International Conference on Natural Language Generation

The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentence along with its syntactic tree, have shown state-of-the-art performance. Recent work shows that a multilayer LSTM language model outperforms competitive statistical syntactic linearization systems without using syntax. In this paper, we study neural syntactic linearization, building a transition-based syntactic linearizer leveraging a feed forward neural network, observing significantly better results compared to LSTM language models on this task.


pdf bib
AMR-to-text Generation with Synchronous Node Replacement Grammar
Linfeng Song | Xiaochang Peng | Yue Zhang | Zhiguo Wang | Daniel Gildea
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

This paper addresses the task of AMR-to-text generation by leveraging synchronous node replacement grammar. During training, graph-to-string rules are learned using a heuristic extraction algorithm. At test time, a graph transducer is applied to collapse input AMRs and generate output sentences. Evaluated on a standard benchmark, our method gives the state-of-the-art result.


pdf bib
Sense Embedding Learning for Word Sense Induction
Linfeng Song | Zhiguo Wang | Haitao Mi | Daniel Gildea
Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics

pdf bib
AMR-to-text generation as a Traveling Salesman Problem
Linfeng Song | Yue Zhang | Xiaochang Peng | Zhiguo Wang | Daniel Gildea
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing


pdf bib
A Synchronous Hyperedge Replacement Grammar based approach for AMR parsing
Xiaochang Peng | Linfeng Song | Daniel Gildea
Proceedings of the Nineteenth Conference on Computational Natural Language Learning


pdf bib
Syntactic SMT Using a Discriminative Text Generation Model
Yue Zhang | Kai Song | Linfeng Song | Jingbo Zhu | Qun Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)


pdf bib
Translation with Source Constituency and Dependency Trees
Fandong Meng | Jun Xie | Linfeng Song | Yajuan Lü | Qun Liu
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing


pdf bib
ETS: An Error Tolerable System for Coreference Resolution
Hao Xiong | Linfeng Song | Fandong Meng | Yang Liu | Qun Liu | Yajuan Lv
Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task

pdf bib
Bagging-based System Combination for Domain Adaption
Linfeng Song | Haitao Mi | Yajuan Lü | Qun Liu
Proceedings of Machine Translation Summit XIII: Papers