ACL2021全部论文列表已经放出，为了以后更加方便地阅读论文，也本着一颗开源之心，花两个晚上的时间对主会议中的论文进行了分类整理，并附上了对应的论文链接。主要包括10个分类，如下：（1）预训练语言模型及应用（58篇）；（2）表征学习（9篇）；（3）问答及检索（42篇）；（4）文本生成（29篇）；（5）摘要（23篇）；（6）小样本（16篇）；（7）对话（32篇）；（8）情感及情绪分析（15篇）；（9）信息抽取（60篇）；（10）其他（21篇）。整理不易，请多多关注、转发、点赞。我们的口号是“生命不止，学习不停”，论文看起来吧。（1）How Good is Your Tokenizer? On the Monolingual Performance ofMultilingual Language Modelshttps://arxiv.org/abs/2012.15613（2）Meta-KD: A Meta Knowledge Distillation Framework for Language ModelCompression across Domainshttps://arxiv.org/abs/2012.01266（3）How is BERT surprised? Layerwise detection of linguistic anomalieshttps://arxiv.org/abs/2105.07452（4）Super Tickets in Pre-Trained Language Models: From Model Compressionto Improving Generalizationhttps://arxiv.org/abs/2105.12002（5）R2D2: Recursive Transformer based on Differentiable Tree forInterpretable Hierarchical Language Modeling（6）IrEne: Interpretable Energy Prediction for Transformershttps://arxiv.org/abs/2106.01199（7）GhostBERT: Generate More Features with Cheap Operations for BERT（8）Syntax-Enhanced Pre-trained Modelhttps://arxiv.org/abs/2012.14116（9）PLOME: Pre-training with Misspelled Knowledge for Chinese SpellingCorrection（10）EnsLM: Ensemble Language Model for Data Diversity by SemanticClustering（11）StructFormer: Joint Unsupervised Induction of Dependency andConstituency Structure from Masked Language Modelinghttps://arxiv.org/abs/2012.00857（12）Convolutions and Self-Attention: Re-interpreting Relative Positionsin Pre-trained Language Modelshttps://arxiv.org/abs/2106.05505（13）Implicit Representations of Meaning in Neural Language Modelhttps://arxiv.org/abs/2106.00737（14）ERICA: Improving Entity and RelationUnderstanding for Pre-trained Language Models via Contrastive Learninghttps://arxiv.org/abs/2012.15022（15）Improving Formality Style Transfer with Context-Aware Rule Injectionhttps://arxiv.org/abs/2106.00210（16）BinaryBERT: Pushing the Limit of BERT Quantizationhttps://arxiv.org/abs/2012.15701（17）Shortformer: Better Language Modeling using Shorter Inputshttps://arxiv.org/abs/2012.15832（18）Making Pre-trained Language Models Better Few-shot Learnershttps://arxiv.org/abs/2012.15723（19）ChineseBERT: Chinese Pretraining Enhanced by Glyph and PinyinInformation（20）Are Pretrained Convolutions Better than Pretrained Transformers?https://arxiv.org/abs/2105.03322（21）ERNIE-Doc: A Retrospective Long-Document Modeling Transformerhttps://arxiv.org/abs/2012.15688（22）LeeBERT: Learned Early Exit for BERT with cross-level optimization（23）Positional Artefacts Propagate Through Masked Language Model Embeddingshttps://arxiv.org/abs/2011.04393（24）Optimizing Deeper Transformers on Small Datasetshttps://arxiv.org/abs/2012.15355(25)When Do You Need Billionsof Words of Pretraining Data?https://arxiv.org/abs/2011.04946（26）Knowledgeable or Educated Guess? Revisiting Language Models asKnowledge Baseshttps://arxiv.org/abs/2106.09231（27）EarlyBERT: Efficient BERT Training via Early-bird Lottery Ticketshttps://arxiv.org/abs/2101.00063（28）SMedBERT: A Knowledge-Enhanced Pre-trained Language Model withStructured Semantics for Medical Text Mining（29）Structural Guidance for Transformer Language Models（30）MPC-BERT: A Pre-Trained Language Model for Multi-Party ConversationUnderstandinghttps://arxiv.org/abs/2106.01541（31）Language Model Evaluation Beyond Perplexityhttps://arxiv.org/abs/2106.00085（32）BERTGen: Multi-task Generation through BERThttps://arxiv.org/abs/2106.03484（33）Pre-training Universal Language Representationhttps://arxiv.org/abs/2105.14478（34）Cascaded Head-colliding Attentionhttps://arxiv.org/abs/2105.14850（35）Parameter-efficient Multi-task Fine-tuning for Transformers viaShared Hypernetworkshttps://arxiv.org/abs/2106.04489（36）Accelerating BERT Inference for Sequence Labeling via Early-Exithttps://arxiv.org/abs/2105.13878（37）AutoTinyBERT: Automatic Hyper-parameter Optimization for EfficientPre-trained Language Models（38）Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapterhttps://arxiv.org/abs/2105.07148（39）On the Effectiveness of Adapter-based Tuning for Pretrained LanguageModel Adaptationhttps://arxiv.org/abs/2106.03164（40）Taming Pre-trained Language Models with N-gram Representations forLow-Resource Domain Adaptation（41）Marginal Utility Diminishes: Exploring the Minimum Knowledge forBERT Knowledge Distillationhttps://arxiv.org/abs/2106.05691（42）Obtaining Better Static Word Embeddings UsingContextual Embedding Modelshttps://arxiv.org/abs/2106.04302（43）Reflective Decoding: Beyond Unidirectional Generation withOff-the-Shelf Language Modelshttps://arxiv.org/abs/2010.08566（44）Reservoir Transformershttps://arxiv.org/abs/2012.15045（45）LexFit: Lexical Fine-Tuning of Pretrained Language Models（46）Selecting Informative Contexts Improves Language Model Fine-tuninghttps://arxiv.org/abs/2005.00175（47）BERT is to NLP what AlexNet is to CV: Can Pre-Trained LanguageModels Identify Analogies?https://arxiv.org/abs/2105.04949（48）Examining the Inductive Bias of Neural Language Models withArtificial Languageshttps://arxiv.org/abs/2106.01044（49）An Empirical Study on Hyperparameter Optimization for Fine-TuningPre-trained Language Modelshttps://arxiv.org/abs/2106.09204（50）BERTAC: Enhancing Transformer-based Language Models withAdversarially Pretrained Convolutional Neural Networks（51）Enabling Lightweight Fine-tuning for Pre-trained Language ModelCompression based on Matrix Product Operatorshttps://arxiv.org/abs/2106.02205（52）Length-Adaptive Transformer: Train Once with Length Drop, UseAnytime with Searchhttps://arxiv.org/abs/2010.07003（53）H-Transformer-1D: Fast One-Dimensional Hierarchical Attention forSequences（54）Hi-Transformer: Hierarchical Interactive Transformer for Efficientand Effective Long Document Modelinghttps://arxiv.org/abs/2106.01040（55）Is Sparse Attention more Interpretable?https://arxiv.org/abs/2106.01087（56）Learning to Generate Task-Specific Adapters from Task Descriptionhttps://arxiv.org/abs/2101.00420（57）Thank you BART! Rewarding Pre-Trained Models Improves FormalityStyle Transferhttps://arxiv.org/abs/2105.06947?context=cs（58）Pre-training is a Hot Topic: Contextualized Document EmbeddingsImprove Topic Coherencehttps://arxiv.org/abs/2004.03974（1）DeCLUTR: Deep Contrastive Learning for Unsupervised TextualRepresentationshttps://arxiv.org/abs/2006.03659（对比学习）（2）Automated Concatenation of Embeddings for Structured Predictionhttps://arxiv.org/abs/2010.05006（3）Lightweight Cross-Lingual Sentence Representation Learninghttps://arxiv.org/abs/2105.13856（4）ConSERT: A Contrastive Framework for Self-Supervised SentenceRepresentation Transferhttps://arxiv.org/abs/2105.11741（5）Dynamic Contextualized Word Embeddingshttps://arxiv.org/abs/2010.12684（6）Self-Guided Contrastive Learning for BERT Sentence Representationshttps://arxiv.org/abs/2106.07345（7）Bootstrapped Unsupervised Sentence Representation Learning（8）Attentive Multiview Text Representation for Differential Diagnosis（9）DefSent: Sentence Embeddings using Definition Sentenceshttps://arxiv.org/abs/2105.04339（1）Evaluating Evaluation Measures for Ordinal Classification andOrdinal Quantification（2）Dual Reader-Parser on Hybrid Textual and Tabular Evidence for OpenDomain Question Answeringhttps://www.amazon.science/publications/dual-reader-parser-on-hybrid-textual-and-tabular-evidence-for-open-domain-question-answering（3）Explanations for CommonsenseQA: New Dataset and Modelshttps://zenodo.org/record/4784281#.YNngJvkzZsY（4）Answering Ambiguous Questions through Generative Evidence Fusion andRound-Trip Predictionhttps://arxiv.org/abs/2011.13137（5）Improving Document Representations by Generating Pseudo QueryEmbeddings for Dense Retrievalhttps://arxiv.org/abs/2105.03599（6）CoSQA: 20,000+ Web Queries for Code Search and Question Answeringhttps://arxiv.org/abs/2105.13239（7）Coreference Reasoning in Machine Reading Comprehensionhttps://arxiv.org/pdf/2012.15573.pdf（8）End-to-End Training of Neural Retrievers for Open-Domain QuestionAnsweringhttps://arxiv.org/abs/2101.00408（9）Few-Shot Question Answering by Pretraining Span Selectionhttps://arxiv.org/abs/2101.00438（10）Integrating Semantics and Neighborhood Information with Graph-DrivenGenerative Models for Document Retrievalhttps://arxiv.org/abs/2105.13066（11）Robustifying Multi-hop QA through Pseudo-Evidentiality Training（12）Learning Dense Representations of Phrases at Scalehttps://arxiv.org/abs/2012.12624（13）Generation-Augmented Retrieval for Open-Domain Question Answeringhttps://arxiv.org/abs/2009.08553（14）xMoCo: Cross Momentum Contrastive Learning for Open-Domain QuestionAnswering（15）TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular andTextual Content in Financehttps://arxiv.org/abs/2105.07624（16）A Semantic-based Method for Unsupervised Commonsense QuestionAnsweringhttps://arxiv.org/abs/2105.14781（17）A Neural Model for Joint Document and Snippet Ranking in QuestionAnswering for Large Document Collectionshttps://arxiv.org/abs/2106.08908（18）Challenges in Information-Seeking QA: Unanswerable Questions andParagraph Retrievalhttps://arxiv.org/abs/2010.11915（19）Question Answering Over Temporal Knowledge Graphshttps://arxiv.org/abs/2106.01515（20）Can Generative Pre-trained Language Models Serve as Knowledge Basesfor Closed-book QA?https://arxiv.org/abs/2106.01561（21）Article Reranking by Memory-Enhanced Key Sentence Matching forDetecting Previously Fact-Checked Claims（22）UnitedQA: A Hybrid Approach for Open Domain Question Answeringhttps://arxiv.org/abs/2101.00178（23）ForecastQA: A Question Answering Challenge for Event Forecastingwith Temporal Text Datahttps://arxiv.org/abs/2005.00792（24）On the Efficacy of Adversarial Data Collection for QuestionAnswering: Results from a Large-Scale Randomized Studyhttps://arxiv.org/abs/2106.00872（25）Multi-task Retrieval for Knowledge-Intensive Taskshttps://arxiv.org/abs/2101.00117（26）Joint Models for Answer Verification in Question Answering Systems（27）Which Linguist Invented the Lightbulb? Presupposition Verificationfor Question-Answeringhttps://arxiv.org/abs/2101.00391（28）Modeling Transitions of Focal Entities for Conversational KnowledgeBase Question Answering（29）A Mutual Information Maximization Approach for the Spurious SolutionProblem in Weakly Supervised Question Answeringhttps://arxiv.org/abs/2106.07174（30）Learn to Resolve Conversational Dependency: A Consistency TrainingFramework for Conversational Question Answering（31）Learning to Perturb Word Embeddings for Out-of-distribution QAhttps://arxiv.org/abs/2105.02692（32）The Curse of Dense Low-Dimensional Information Retrieval for LargeIndex Sizeshttps://arxiv.org/abs/2012.14210（33）DuReader_robust: A Chinese Dataset Towards Evaluating Robustness andGeneralization of Machine Reading Comprehension in Real-World Applicationshttps://arxiv.org/abs/2004.11142（34）Towards a more Robust Evaluation for Conversational QuestionAnswering（35）Training Adaptive Computation for Open-DomainQuestion Answering with Computational Constraints（36）Efficient Passage Retrieval with Hashing for Open-domain QuestionAnsweringhttps://arxiv.org/abs/2106.00882（37）Using Adversarial Attacks to Reveal the Statistical Bias in MachineReading Comprehension Modelshttps://arxiv.org/abs/2105.11136（38）VAULT: VAriable Unified Long Text Representation for Machine ReadingComprehensionhttps://arxiv.org/abs/2105.03229（39）Towards more equitable question answering systems: How much moredata do you need?https://arxiv.org/abs/2105.14115（40）A Semantics-aware Transformer Model of Relation Linking forKnowledge Base Question Answering（41）Neural Retrieval for Question Answering with Cross-AttentionSupervised Data Augmentationhttps://arxiv.org/abs/2009.13815（42）Addressing Semantic Drift in Generative Question Answering withAuxiliary Extraction（1）Generalising Multilingual Concept-to-Text NLG with Language AgnosticDelexicalisationhttps://arxiv.org/abs/2105.03432（2）Prefix-Tuning: Optimizing Continuous Prompts for Generationhttps://arxiv.org/abs/2101.00190（3）Polyjuice: Generating Counterfactuals for Explaining, Evaluating,and Improving Modelshttps://arxiv.org/abs/2101.00288（4）Competence-based Multimodal Curriculum Learning for Medical ReportGeneration（5）BACO: A Background Knowledge- and Content-Based Framework for CitingSentence Generation（6）Mention Flags (MF): Constraining Transformer-based Text Generators（7）Guiding the Growth: Difficulty-Controllable Question Generationthrough Step-by-Step Rewritinghttps://arxiv.org/abs/2105.11698（8）Improving Encoder by Auxiliary Supervision Tasks for Table-to-TextGeneration（9）Writing by Memorizing:Hierarchical Retrieval-based Medical Report Generationhttps://arxiv.org/abs/2106.06471（10）Data Augmentation for TextGeneration Without Any Augmented Datahttps://arxiv.org/abs/2105.13650（11）Long Text Generation byModeling Sentence-Level and Discourse-Level Coherencehttps://arxiv.org/abs/2105.08963（12）PENS: A Dataset and GenericFramework for Personalized News Headline Generationhttps://www.microsoft.com/en-us/research/uploads/prod/2021/06/ACL2021_PENS_Camera_Ready_1862_Paper.pdf（13）De-Confounded VariationalEncoder-Decoder for Logical Table-to-Text Generation（14）Bridging Subword Gaps inPretrain-Finetune Paradigm for Natural Language Generationhttps://arxiv.org/abs/2106.06125（15）Employing ArgumentationKnowledge Graphs for Neural Argument Generation（16）Select, Extract andGenerate: Neural Keyphrase Generation with Layer-wise Coverage Attentionhttps://arxiv.org/abs/2008.01739（17）DESCGEN: A DistantlySupervised Datasetfor Generating Entity Descriptionshttps://arxiv.org/abs/2106.05365（18）GTM: A Generative Triple-wiseModel for Conversational Question Generationhttps://arxiv.org/abs/2106.03635（19）All That’s ‘Human’ Is NotGold: Evaluating Human Evaluation of Generated Text（20）A Hierarchical VAE forCalibrating Attributes while Generating Text using Normalizing Flow（21）DYPLOC: Dynamic Planning ofContent Using Mixed Language Models for Text Generationhttps://arxiv.org/abs/2106.00791（22）Controllable Open-endedQuestion Generation with A New Question Type Ontologyhttps://web.eecs.umich.edu/~wangluxy/papers/ACL2021_cao_wang.pdf（23）DExperts: Decoding-TimeControlled Text Generation with Experts and Anti-Expertshttps://arxiv.org/abs/2105.03023（24）Towards Table-to-TextGeneration with Numerical Reasoning（25）TGEA: An Error-AnnotatedDataset and Benchmark Tasks for TextGeneration from Pretrained Language Models（26）On Training InstanceSelection for Few-Shot Neural Text Generation（27）How Helpful is InverseReinforcement Learning for Table-to-Text Generation?（28）QuestionGeneration for Adaptive Educationhttps://arxiv.org/abs/2106.04262（29）Avoiding Overlap in DataAugmentation for AMR-to-Text Generation（1）Cross-Lingual Abstractive Summarization with Limited ParallelResourceshttps://arxiv.org/abs/2105.13648（2）Unsupervised Extractive Summarization-Based Representations forAccurate and Explainable Collaborative Filtering（3）Improving Factual Consistency of Abstractive Summarization viaQuestion Answeringhttps://arxiv.org/abs/2105.04623（4）Long-Span Summarization via Local Attention and Content Selectionhttps://arxiv.org/abs/2105.03801（5）RepSum: Unsupervised Dialogue Summarization based on ReplacementStrategy（6）TWAG: A Topic-Guided Wikipedia Abstract Generator（7）Language Model as an Annotator: Exploring DialoGPT for DialogueSummarizationhttps://arxiv.org/abs/2105.12544（8）BASS: Boosting Abstractive Summarization with Unified Semantic Graphhttps://arxiv.org/abs/2105.12041（9）Focus Attention: Promoting Faithfulness and Diversity inSummarizationhttps://arxiv.org/abs/2105.11921（10）Deep Differential Amplifier for Extractive Summarization（11）Generating Query Focused Summaries from Query-Free Resourceshttps://arxiv.org/abs/2012.14774（12）PASS: Perturb-and-Select Summarizer for Product Reviewshttps://www.amazon.science/publications/pass-perturb-and-select-summarizer-for-product-reviews（13）ConvoSumm: Conversation Summarization Benchmark and ImprovedAbstractive Summarization with Argument Mininghttps://arxiv.org/abs/2106.00829（14）Multi-TimeLine Summarization (MTLS): Improving TimelineSummarization by Generating Multiple Summaries（15）EmailSum: Abstractive Email Thread Summarization（16）Dissecting Generation Modes for Abstractive Summarization Models viaAblation and Attributionhttps://arxiv.org/abs/2106.01518（17）A Training-free and Reference-free Summarization Evaluation Metricvia Centrality-weighted Relevance and Self-referenced Redundancyhttps://arxiv.org/abs/2106.13945（18）Generating SOAP Notes from Doctor-Patient Conversations UsingModular Summarization Techniqueshttps://arxiv.org/abs/2005.01795（19）WikiSum: Coherent Summarization Dataset forEfficient Human-Evaluationhttps://registry.opendata.aws/wikisum/（20）Bringing Structure into Summaries: a Faceted Summarization Datasetfor Long Scientific Documentshttps://arxiv.org/abs/2106.00130（21）Reinforcement Learning for Abstractive Question Summarization withQuestion-aware Semantic Rewards（22）Demoting the Lead Bias in News Summarization via AlternatingAdversarial Learninghttps://arxiv.org/abs/2105.14241（23）SimCLS: A Simple Framework for Contrastive Learning of AbstractiveSummarizationhttps://arxiv.org/abs/2106.01890（1）Meta-KD: A Meta Knowledge Distillation Framework for Language ModelCompression across Domainshttps://arxiv.org/abs/2012.01266（2）Multi-Label Few-Shot Learning for Aspect Category Detectionhttps://arxiv.org/abs/2105.14174（3）ProtAugment: Intent Detection Meta-Learning through UnsupervisedDiverse Paraphrasinghttps://arxiv.org/abs/2105.12995（4）Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervisionhttps://arxiv.org/abs/2012.14862（5）AugNLG: Few-shot Natural Language Generation using Self-trained DataAugmentationhttps://arxiv.org/abs/2106.05589（6）A Pre-training Strategy for Zero-Resource Response Selection inKnowledge-Grounded Conversations（7）Evaluatingmorphological typology in zero-shot cross-lingual transfer（8）LexiconLearning for Few Shot Sequence Modelinghttps://arxiv.org/abs/2106.03993（9）To POS Tagor Not to POS Tag: The Impact of POS Tags on Morphological Learning inLow-Resource Settings（10）Meta-Learningto Compositionally Generalizehttps://arxiv.org/abs/2106.04252（11）RiskMinimization for Zero-shot Sequence Labelinghttp://faculty.sist.shanghaitech.edu.cn/faculty/tukw/acl21rm.pdf（12）QA-DrivenZero-shot Slot Filling with Weak Supervision Pretraining（13）Zero-shotFact Verification by Claim Generationhttps://arxiv.org/abs/2105.14682（14）DistinctLabel Representations for Few-Shot Text Classification（15）Zero-shot Event Extraction via Transfer Learning: Challenges andInsights（16）Issues with Entailment-based Zero-shot Text Classification（1）TicketTalk: Toward human-level performance with end-to-end,transaction-based dialog systemshttps://arxiv.org/abs/2012.12458（2）SocAoG: Incremental Graph Parsing for Social Relation Inference inDialogueshttps://arxiv.org/abs/2106.01006（3）HERALD: An Annotation Efficient Method to Detect User Disengagementin Social Conversationshttps://arxiv.org/abs/2106.00162（4）Comprehensive Study: How the Context Information of DifferentGranularity Affects Dialogue State Tracking?https://arxiv.org/abs/2105.03571（5）Discovering Dialog Structure Graph for Coherent Dialog Generation（6）Dialogue Response Selection with Hierarchical Curriculum Learninghttps://arxiv.org/abs/2012.14756（7）Diversifying Dialog Generation via Adaptive Label Smoothinghttps://arxiv.org/abs/2105.14556（8）BoB: BERT Over BERT for Training Persona-based Dialogue Models fromLimited Personalized Datahttps://arxiv.org/abs/2106.06169（9）I like fish, especially dolphins: Addressing Contradictions inDialogue Modelinghttps://arxiv.org/abs/2012.13391（10）Towards Quantifiable Dialogue Coherence Evaluationhttps://arxiv.org/abs/2106.00507（11）A Sequence-to-Sequence Approach to Dialogue State Trackinghttps://arxiv.org/abs/2011.09553（12）Dual Slot Selector via Local Reliability Verification for DialogueState Tracking（13）Learning from Perturbations: Diverse and Informative DialogueGeneration with Inverse Adversarial Traininghttps://arxiv.org/abs/2105.15171（14）Novel Slot Detection: A Benchmark for Discovering Unknown Slot Typesin the Task-Oriented Dialogue Systemhttps://arxiv.org/abs/2105.14313（15）RADDLE: An Evaluation Benchmark and Analysis Platform for RobustTask-oriented Dialog Systemshttps://arxiv.org/abs/2012.14666（16）Learning to Ask Conversational Questions by Optimizing LevenshteinDistance（17）Conversations Are Not Flat: Modeling the Dynamic Information Flowacross Dialogue Utterances https://arxiv.org/abs/2106.02227（18）Semantic Representation for Dialogue Modelinghttps://arxiv.org/abs/2105.10188（19）Towards Emotional Support Dialog Systemshttps://arxiv.org/abs/2106.01144（20）Discovering Dialogue Slots with Weak Supervision（21）Structural Pre-training for Dialogue Comprehensionhttps://arxiv.org/abs/2105.10956（22）Transferable Dialogue Systems and User Simulators（23）Improving Dialog Systems for Negotiation with Personality Modeling（24）TIMEDIAL: Temporal Commonsense Reasoning in Dialoghttps://arxiv.org/abs/2106.04571（25）Increasing Faithfulness in Knowledge-Grounded Dialogue withControllable Features（26）GL-GIN: Fast and Accurate Non-Autoregressive Model for JointMultiple Intent Detection and Slot Fillinghttps://arxiv.org/abs/2106.01925（27）DynaEval: Unifying Turn and Dialogue Level Evaluationhttps://arxiv.org/abs/2106.01112（28）Saying No is An Art: Contextualized Fallback Responses forUnanswerable Dialogue Querieshttps://arxiv.org/abs/2012.01873（29）Preview, Attend and Review: Schema-Aware Curriculum Learning forMulti-Domain Dialogue State Trackinghttps://arxiv.org/abs/2106.00291（30）Continual Learning for Task-oriented Dialogue System with IterativeNetwork Pruning, Expanding and Masking（31）Domain-Adaptive Pretraining Methods for Dialogue Understandinghttps://arxiv.org/abs/2105.13665（32）PRAL: A Tailored Pre-Training Model for Task-Oriented DialogGenerationhttps://arxiv.org/abs/2004.13835（1）Dual Graph Convolutional Networks for Aspect-based SentimentAnalysis（2）Directed Acyclic Graph Network for Conversational EmotionRecognitionhttps://arxiv.org/abs/2105.12907（3）DynaSent: A Dynamic Benchmark for Sentiment Analysishttps://arxiv.org/abs/2012.15349（4）Position Bias Mitigation: A Knowledge-Aware Graph Model for EmotionCause Extractionhttps://arxiv.org/abs/2106.03518（5）Topic-Driven and Knowledge-Aware Transformer for Dialogue EmotionDetectionhttps://arxiv.org/abs/2106.01071（6）Distributed Representations of Emotion Categories in Emotion Space（7）DialogueCRN: Contextual Reasoning Networks for Emotion Recognitionin Conversationshttps://arxiv.org/abs/2106.01978（8）Missing Modality Imagination Network for Emotion Recognition withUncertain Missing Modalities（9）A Unified Generative Framework for Aspect-based Sentiment Analysishttps://arxiv.org/abs/2106.04300（10）Exploring the Efficacy of Automatically Generated Counterfactualsfor Sentiment Analysis（11）Structured Sentiment Analysis as Dependency Graph Parsinghttps://arxiv.org/abs/2105.14504（12）Aspect-Category-Opinion-Sentiment Quadruple Extraction with ImplicitAspects and Opinions（13）Deep Context- and Relation-Aware Learning for Aspect-based SentimentAnalysishttps://arxiv.org/abs/2106.03806（14）Towards Generative Aspect-Based Sentiment Analysis（15）eMLM: A New Pre-training Objective for Emotion Related Tasks（1）Named Entity Recognition with Small Strongly Labeled and LargeWeakly Labeled Datahttps://arxiv.org/abs/2106.08977（2）Competence-based Multimodal Curriculum Learning for Medical ReportGenerationhttps://arxiv.org/abs/2105.06804（3）OntoED: Low-resource Event Detection with Ontology Embeddinghttps://arxiv.org/abs/2105.10922（4）Subsequence Based Deep Active Learning for Named Entity Recognition（5）BERTifying the Hidden Markov Model for Multi-Source WeaklySupervised Named Entity Recognitionhttps://arxiv.org/abs/2105.12848（6）Knowledge-Enriched Event Causality Identification via LatentStructure Induction Networks（7）Document-level Event Extraction via Heterogeneous Graph-basedInteraction Model with a Trackerhttps://arxiv.org/abs/2105.14924（8）A Large-Scale Chinese Multimodal NER Dataset with Speech Clues（9）LearnDA: Learnable Knowledge-Guided Data Augmentation for EventCausality Identificationhttps://arxiv.org/abs/2106.01649（10）CIL: Contrastive Instance Learning Framework for DistantlySupervised Relation Extractionhttps://arxiv.org/abs/2106.10855（11）Few-NERD: A Few-shot Named Entity Recognition Datasethttps://arxiv.org/abs/2105.07464（12）SENT: Sentence-level Distant Relation Extraction via NegativeTraininghttps://arxiv.org/abs/2106.11566?context=cs（13）Modularized Interaction Network for Named Entity Recognition（14）Capturing Event Argument Interaction via A Bi-DirectionalEntity-Level Recurrent Decoder（15）A Span-Based Model for Joint Overlapped and Discontinuous NamedEntity Recognition（16）An End-to-End Progressive Multi-Task Learning Framework for MedicalNamed Entity Recognition and Normalization（17）MLBiNet: A Cross-Sentence Collective Event Detection Networkhttps://arxiv.org/abs/2105.09458（18）PRGC: Potential Relation and Global Correspondence Based JointRelational Triple Extractionhttps://arxiv.org/abs/2106.09895（20）Improving Named Entity Recognition by External Context Retrievingand Cooperative Learninghttps://arxiv.org/abs/2105.03654（21）Leveraging Type Descriptions for Zero-shot Named Entity Recognitionand Classification（22）Revisiting the Negative Data of Distantly Supervised RelationExtractionhttps://arxiv.org/abs/2105.10158（23）Learning from Miscellaneous Other-Class Words for Few-shot NamedEntity Recognition（24）Joint Biomedical Entity and Relation Extraction withKnowledge-Enhanced Collective Inferencehttps://arxiv.org/abs/2105.13456（25）Nested Named Entity Recognition via Explicitly Excluding theInfluence of the Best Path（27）How Knowledge Graph and Attention Help? A Qualitative Analysis intoBag-level Relation Extraction（28）From Discourse to Narrative: Knowledge Projection for Event RelationExtractionhttps://arxiv.org/abs/2106.08629（29）Fine-grained Information Extraction from Biomedical Literature basedon Knowledge-enriched Abstract Meaning Representation（30）A Unified Generative Framework for Various NER Subtaskshttps://arxiv.org/abs/2106.01223（31）MECT: Multi-Metadata Embedding based Cross-Transformer for ChineseNamed Entity Recognition（32）Unleash GPT-2 Power for Event Detection（33）Trigger is Not Sufficient: Exploiting Frame-aware Knowledge forImplicit Event Argument Extraction（34）Element Intervention for Open Relation Extractionhttps://arxiv.org/abs/2106.09558（35）Text2Event: Controllable Sequence-to-Structure Generation forEnd-to-end Event Extractionhttps://arxiv.org/abs/2106.09232（36）CLEVE: Contrastive Pre-training for Event Extractionhttps://arxiv.org/abs/2105.14485（37）MulDA: A Multilingual Data Augmentation Framework for Low-ResourceCross-Lingual NERhttps://raihanjoty.github.io/papers/linlin-et-al-acl-21.html（38）De-biasing Distantly Supervised Named Entity Recognition via CausalInterventionhttps://arxiv.org/abs/2106.09233（39）UniRE: A Unified Label Space for Entity Relation Extraction（40）Crowdsourcing Learning as Domain Adaptation: A Case Study on NamedEntity Recognitionhttps://arxiv.org/abs/2105.14980（41）Modeling Fine-Grained Entity Types with Box Embeddingshttps://arxiv.org/abs/2101.00345（42）CoRI: Collective Relation Integration with Data Augmentation forOpen Information Extractionhttps://arxiv.org/abs/2106.00793（43）CitationIE: Leveraging the Citation Graph for Scientific InformationExtractionhttps://arxiv.org/abs/2106.01560（44）Dependency-driven Relation Extraction with Attentive GraphConvolutional Networks（45）Discontinuous Named Entity Recognition as Maximal Clique Discoveryhttps://arxiv.org/abs/2106.00218（46）Weakly Supervised Named Entity Tagging with Learnable Logical Rules（47）SpanNER: Named Entity Re-/Recognition as Span Predictionhttps://arxiv.org/abs/2106.00641（48）Refining Sample Embeddings with Relation Prototypes to EnhanceContinual Relation Extractionhttps://www.researchgate.net/publication/352257560_Refining_Sample_Embeddings_with_Relation_Prototypes_to_Enhance_Continual_Relation_Extraction（49）Document-level Event Extraction via Parallel Prediction Networks（50）Learning Span-Level Interactions for Aspect Sentiment TripletExtraction（51）The Possible, the Plausible, and the Desirable: Event-Based ModalityDetection for Language Processinghttps://arxiv.org/abs/2106.08037（52）A Neural Transition-based Joint Model for Disease Named EntityRecognition and Normalization（53）TIMERS: Document-level Temporal Relation Extraction（54）ROPE: Reading Order Equivariant Positional Encoding for Graph-basedDocument Information Extractionhttps://arxiv.org/abs/2106.10786（55）Enhancing Entity Boundary Detection for Better Chinese Named EntityRecognition（56）Entity Enhancement for Implicit Discourse Relation Classification inthe Biomedical Domain（57）Entity Concept-enhanced Few-shot Relation Extractionhttps://arxiv.org/abs/2106.02401（58）Improving Model Generalization: A Chinese Named Entity RecognitionCase Study（59）Explicitly Capturing Relations between Entity Mentions via GraphNeural Networks for Domain-specific Named Entity Recognition（60）Three Sentences Are All You Need: Local Path Enhanced DocumentRelation Extractionhttps://arxiv.org/abs/2106.01793（1）Semi-Supervised Text Classification with Balanced DeepRepresentation Distributions（2）Defense against Adversarial Attacks in NLP via DirichletNeighborhood Ensemblehttps://arxiv.org/abs/2006.11627（3）Inter-GPS: Interpretable Geometry Problem Solving with FormalLanguage and Symbolic Reasoninghttps://arxiv.org/abs/2105.04165（4）Improving the Faithfulness of Attention-based Explanations withTask-specific Information for Text Classificationhttps://arxiv.org/abs/2105.02657（5）Concept-Based Label Embedding via Dynamic Routing for HierarchicalText Classification（6）Joint Verification and Reranking for Open Fact Checking Over Tableshttps://arxiv.org/abs/2012.15115（7）Structural Knowledge Distillation: Tractably Distilling Informationfor Structured Predictorhttps://arxiv.org/abs/2010.05010（8）UnNatural Language Inferencehttps://arxiv.org/abs/2101.00010（9）OoMMix: Out-of-manifold Regularization in Contextual Embedding Spacefor Text Classificationhttps://arxiv.org/abs/2105.06750（10）Database Reasoning Over Texthttps://arxiv.org/abs/2106.01074（11）Towards Robustness of Text-to-SQL Models against SynonymSubstitutionhttps://arxiv.org/abs/2106.01065（12）Determinantal Beam Searchhttps://arxiv.org/abs/2106.07400（13）POS-Constrained Parallel Decoding for Non-autoregressive Generation（14）Hierarchy-aware Label Semantics Matching Network for HierarchicalText Classification（15）Multi-View Cross-Lingual Structured Prediction with MinimumSupervisionhttp://faculty.sist.shanghaitech.edu.cn/faculty/tukw/acl21mv.pdf（16）Chase: A Large-Scale and Pragmatic Chinese Dataset forCross-Database Context-Dependent Text-to-SQL（17）Factoring Statutory Reasoning as Language Understanding Challengeshttps://arxiv.org/abs/2105.07903（18）HiddenCut: Simple Data Augmentation for Natural LanguageUnderstanding with Better Generalizationhttps://arxiv.org/abs/2106.00149（19）KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsershttps://arxiv.org/abs/2106.11455（20）Automatic ICD Coding via Interactive Shared Representation Networkswith Self-distillation Mechanism（21）Alignment Rationale for Natural Language Inference由于本人涉及领域问题，没有对机器翻译、多模态、多语言等相关论文进行整理。如果有兴趣的朋友，可以整理后，私聊我，对该文进行增补。
原创不易，为爱发电。
知乎：刘聪NLP，文章同步在知乎更新，大家可以关注一波。