2021-07-09

转自：NLP工作站 知乎 刘聪NLP

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）。

update：刘聪NLP：ACL2021 Findings论文汇总及分类

一、 预训练语言模型及应用
Long

（1）How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models

https://arxiv.org/abs/2012.15613

（2）Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

https://arxiv.org/abs/2012.01266

（3）How is BERT surprised? Layerwise detection of linguistic anomalies

https://arxiv.org/abs/2105.07452

（4）Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization

https://arxiv.org/abs/2105.12002

（5）R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling

（6）IrEne: Interpretable Energy Prediction for Transformers

https://arxiv.org/abs/2106.01199

（7）GhostBERT: Generate More Features with Cheap Operations for BERT

（8）Syntax-Enhanced Pre-trained Model

https://arxiv.org/abs/2012.14116

（9）PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction

（10）EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering

（11）StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling

https://arxiv.org/abs/2012.00857

（12）Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models

https://arxiv.org/abs/2106.05505

（13）Implicit Representations of Meaning in Neural Language Model

https://arxiv.org/abs/2106.00737

（14）ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning

https://arxiv.org/abs/2012.15022

（15）Improving Formality Style Transfer with Context-Aware Rule Injection

https://arxiv.org/abs/2106.00210

（16）BinaryBERT: Pushing the Limit of BERT Quantization

https://arxiv.org/abs/2012.15701

（17）Shortformer: Better Language Modeling using Shorter Inputs

https://arxiv.org/abs/2012.15832

（18）Making Pre-trained Language Models Better Few-shot Learners

https://arxiv.org/abs/2012.15723

（19）ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information

（20）Are Pretrained Convolutions Better than Pretrained Transformers?

https://arxiv.org/abs/2105.03322

（21）ERNIE-Doc: A Retrospective Long-Document Modeling Transformer

https://arxiv.org/abs/2012.15688

（22）LeeBERT: Learned Early Exit for BERT with cross-level optimization

（23）Positional Artefacts Propagate Through Masked Language Model Embeddings

https://arxiv.org/abs/2011.04393

（24）Optimizing Deeper Transformers on Small Datasets

https://arxiv.org/abs/2012.15355

(25) When Do You Need Billions of Words of Pretraining Data?

https://arxiv.org/abs/2011.04946

（26）Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases

https://arxiv.org/abs/2106.09231

（27）EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

https://arxiv.org/abs/2101.00063

（28）SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining

（29）Structural Guidance for Transformer Language Models

（30）MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding

https://arxiv.org/abs/2106.01541

（31）Language Model Evaluation Beyond Perplexity

https://arxiv.org/abs/2106.00085

（32）BERTGen: Multi-task Generation through BERT

https://arxiv.org/abs/2106.03484

（33）Pre-training Universal Language Representation

https://arxiv.org/abs/2105.14478

（34）Cascaded Head-colliding Attention

https://arxiv.org/abs/2105.14850

（35）Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks

https://arxiv.org/abs/2106.04489

（36）Accelerating BERT Inference for Sequence Labeling via Early-Exit

https://arxiv.org/abs/2105.13878

（37）AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models

（38）Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

https://arxiv.org/abs/2105.07148

（39）On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation

https://arxiv.org/abs/2106.03164

（40）Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation

（41）Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

https://arxiv.org/abs/2106.05691

（42）Obtaining Better Static Word Embeddings Using Contextual Embedding Models

https://arxiv.org/abs/2106.04302

（43）Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models

https://arxiv.org/abs/2010.08566

（44）Reservoir Transformers

https://arxiv.org/abs/2012.15045

（45）LexFit: Lexical Fine-Tuning of Pretrained Language Models

（46）Selecting Informative Contexts Improves Language Model Fine-tuning

https://arxiv.org/abs/2005.00175

（47）BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?

https://arxiv.org/abs/2105.04949

（48）Examining the Inductive Bias of Neural Language Models with Artificial Languages

https://arxiv.org/abs/2106.01044

（49）An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models

https://arxiv.org/abs/2106.09204

（50）BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks

（51）Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators

https://arxiv.org/abs/2106.02205

（52）Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search

https://arxiv.org/abs/2010.07003

（53）H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

Short

（54）Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

https://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 Description

https://arxiv.org/abs/2101.00420

（57）Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer

https://arxiv.org/abs/2105.06947?context=cs

（58）Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence

https://arxiv.org/abs/2004.03974

二、 表征学习
Long

（1）DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations

https://arxiv.org/abs/2006.03659（对比学习）

（2）Automated Concatenation of Embeddings for Structured Prediction

https://arxiv.org/abs/2010.05006

（3）Lightweight Cross-Lingual Sentence Representation Learning

https://arxiv.org/abs/2105.13856

（4）ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

https://arxiv.org/abs/2105.11741

（5）Dynamic Contextualized Word Embeddings

https://arxiv.org/abs/2010.12684

（6）Self-Guided Contrastive Learning for BERT Sentence Representations

https://arxiv.org/abs/2106.07345

（7）Bootstrapped Unsupervised Sentence Representation Learning

Short

（8）Attentive Multiview Text Representation for Differential Diagnosis

Short

（9）DefSent: Sentence Embeddings using Definition Sentences

https://arxiv.org/abs/2105.04339

三、 问答及检索
Long

（1）Evaluating Evaluation Measures for Ordinal Classification and Ordinal Quantification

（2）Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

https://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 Models

https://zenodo.org/record/4784281#.YNngJvkzZsY

（4）Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction

https://arxiv.org/abs/2011.13137

（5）Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval

https://arxiv.org/abs/2105.03599

（6）CoSQA: 20,000+ Web Queries for Code Search and Question Answering

https://arxiv.org/abs/2105.13239

（7）Coreference Reasoning in Machine Reading Comprehension

https://arxiv.org/pdf/2012.15573.pdf

（8）End-to-End Training of Neural Retrievers for Open-Domain Question Answering

https://arxiv.org/abs/2101.00408

（9）Few-Shot Question Answering by Pretraining Span Selection

https://arxiv.org/abs/2101.00438

（10）Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval

https://arxiv.org/abs/2105.13066

（11）Robustifying Multi-hop QA through Pseudo-Evidentiality Training

（12）Learning Dense Representations of Phrases at Scale

https://arxiv.org/abs/2012.12624

（13）Generation-Augmented Retrieval for Open-Domain Question Answering

https://arxiv.org/abs/2009.08553

（14）xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering

（15）TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance

https://arxiv.org/abs/2105.07624

（16）A Semantic-based Method for Unsupervised Commonsense Question Answering

https://arxiv.org/abs/2105.14781

（17）A Neural Model for Joint Document and Snippet Ranking in Question Answering for Large Document Collections

https://arxiv.org/abs/2106.08908

（18）Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrieval

https://arxiv.org/abs/2010.11915

（19）Question Answering Over Temporal Knowledge Graphs

https://arxiv.org/abs/2106.01515

（20）Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?

https://arxiv.org/abs/2106.01561

（21）Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

（22）UnitedQA: A Hybrid Approach for Open Domain Question Answering

https://arxiv.org/abs/2101.00178

（23）ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data

https://arxiv.org/abs/2005.00792

（24）On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study

https://arxiv.org/abs/2106.00872

（25）Multi-task Retrieval for Knowledge-Intensive Tasks

https://arxiv.org/abs/2101.00117

（26）Joint Models for Answer Verification in Question Answering Systems

（27）Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering

https://arxiv.org/abs/2101.00391

（28）Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering

（29）A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering

https://arxiv.org/abs/2106.07174

（30）Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering

（31）Learning to Perturb Word Embeddings for Out-of-distribution QA

https://arxiv.org/abs/2105.02692

Short

（32）The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes

https://arxiv.org/abs/2012.14210

（33）DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications

https://arxiv.org/abs/2004.11142

（34）Towards a more Robust Evaluation for Conversational Question Answering

（35）Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints

（36）Efficient Passage Retrieval with Hashing for Open-domain Question Answering

https://arxiv.org/abs/2106.00882

（37）Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models

https://arxiv.org/abs/2105.11136

（38）VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension

https://arxiv.org/abs/2105.03229

（39）Towards more equitable question answering systems: How much more data do you need?

https://arxiv.org/abs/2105.14115

（40）A Semantics-aware Transformer Model of Relation Linking for Knowledge Base Question Answering

（41）Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation

https://arxiv.org/abs/2009.13815

（42）Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction

四、 文本生成
Long

（1）Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation

https://arxiv.org/abs/2105.03432

（2）Prefix-Tuning: Optimizing Continuous Prompts for Generation

https://arxiv.org/abs/2101.00190

（3）Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

https://arxiv.org/abs/2101.00288

（4）Competence-based Multimodal Curriculum Learning for Medical Report Generation

（5）BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation

（6）Mention Flags (MF): Constraining Transformer-based Text Generators

（7）Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

https://arxiv.org/abs/2105.11698

（8）Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation

（9）Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation

https://arxiv.org/abs/2106.06471

（10）Data Augmentation for Text Generation Without Any Augmented Data

https://arxiv.org/abs/2105.13650

（11）Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence

https://arxiv.org/abs/2105.08963

（12）PENS: A Dataset and Generic Framework for Personalized News Headline Generation

https://www.microsoft.com/en-us/research/uploads/prod/2021/06/ACL2021_PENS_Camera_Ready_1862_Paper.pdf

（13）De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation

（14）Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation

https://arxiv.org/abs/2106.06125

（15）Employing Argumentation Knowledge Graphs for Neural Argument Generation

（16）Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attention

https://arxiv.org/abs/2008.01739

（17）DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions

https://arxiv.org/abs/2106.05365

（18）GTM: A Generative Triple-wise Model for Conversational Question Generation

https://arxiv.org/abs/2106.03635

（19）All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text

（20）A Hierarchical VAE for Calibrating Attributes while Generating Text using Normalizing Flow

（21）DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation

https://arxiv.org/abs/2106.00791

（22）Controllable Open-ended Question Generation with A New Question Type Ontology

https://web.eecs.umich.edu/~wangluxy/papers/ACL2021_cao_wang.pdf

（23）DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts

https://arxiv.org/abs/2105.03023

（24）Towards Table-to-Text Generation with Numerical Reasoning

（25）TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models

Short

（26）On Training Instance Selection for Few-Shot Neural Text Generation

（27）How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation?

（28）Question Generation for Adaptive Education

https://arxiv.org/abs/2106.04262

（29）Avoiding Overlap in Data Augmentation for AMR-to-Text Generation

五、 摘要
Long

（1）Cross-Lingual Abstractive Summarization with Limited Parallel Resources

https://arxiv.org/abs/2105.13648

（2）Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering

（3）Improving Factual Consistency of Abstractive Summarization via Question Answering

https://arxiv.org/abs/2105.04623

（4）Long-Span Summarization via Local Attention and Content Selection

https://arxiv.org/abs/2105.03801

（5）RepSum: Unsupervised Dialogue Summarization based on Replacement Strategy

（6）TWAG: A Topic-Guided Wikipedia Abstract Generator

（7）Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization

https://arxiv.org/abs/2105.12544

（8）BASS: Boosting Abstractive Summarization with Unified Semantic Graph

https://arxiv.org/abs/2105.12041

（9）Focus Attention: Promoting Faithfulness and Diversity in Summarization

https://arxiv.org/abs/2105.11921

（10）Deep Differential Amplifier for Extractive Summarization

（11）Generating Query Focused Summaries from Query-Free Resources

https://arxiv.org/abs/2012.14774

（12）PASS: Perturb-and-Select Summarizer for Product Reviews

https://www.amazon.science/publications/pass-perturb-and-select-summarizer-for-product-reviews

（13）ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining

https://arxiv.org/abs/2106.00829

（14）Multi-TimeLine Summarization (MTLS): Improving Timeline Summarization by Generating Multiple Summaries

（15）EmailSum: Abstractive Email Thread Summarization

（16）Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution

https://arxiv.org/abs/2106.01518

（17）A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance and Self-referenced Redundancy

https://arxiv.org/abs/2106.13945

（18）Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques

https://arxiv.org/abs/2005.01795

Short

（19）WikiSum: Coherent Summarization Dataset for Efficient Human-Evaluation

https://registry.opendata.aws/wikisum/

（20）Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents

https://arxiv.org/abs/2106.00130

（21）Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards

（22）Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

https://arxiv.org/abs/2105.14241

（23）SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization

https://arxiv.org/abs/2106.01890

六、 小样本
Long
（1）Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

https://arxiv.org/abs/2012.01266

（2）Multi-Label Few-Shot Learning for Aspect Category Detection

https://arxiv.org/abs/2105.14174

（3）ProtAugment: Intent Detection Meta-Learning through Unsupervised Diverse Paraphrasing

https://arxiv.org/abs/2105.12995

（4）Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision

https://arxiv.org/abs/2012.14862

（5）AugNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation

https://arxiv.org/abs/2106.05589

（6）A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations

（7）Evaluating morphological typology in zero-shot cross-lingual transfer

（8）Lexicon Learning for Few Shot Sequence Modeling

https://arxiv.org/abs/2106.03993

（9）To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings

（10）Meta-Learning to Compositionally Generalize

https://arxiv.org/abs/2106.04252

（11）Risk Minimization for Zero-shot Sequence Labeling

http://faculty.sist.shanghaitech.edu.cn/faculty/tukw/acl21rm.pdf

Short

（12）QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining

（13）Zero-shot Fact Verification by Claim Generation

https://arxiv.org/abs/2105.14682

（14）Distinct Label Representations for Few-Shot Text Classification

（15）Zero-shot Event Extraction via Transfer Learning: Challenges and Insights

（16）Issues with Entailment-based Zero-shot Text Classification

七、 对话
Long

（1）TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems

https://arxiv.org/abs/2012.12458

（2）SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues

https://arxiv.org/abs/2106.01006

（3）HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations

https://arxiv.org/abs/2106.00162

（4）Comprehensive Study: How the Context Information of Different Granularity 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 Learning

https://arxiv.org/abs/2012.14756

（7）Diversifying Dialog Generation via Adaptive Label Smoothing

https://arxiv.org/abs/2105.14556

（8）BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data

https://arxiv.org/abs/2106.06169

（9）I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling

https://arxiv.org/abs/2012.13391

（10）Towards Quantifiable Dialogue Coherence Evaluation

https://arxiv.org/abs/2106.00507

（11）A Sequence-to-Sequence Approach to Dialogue State Tracking

https://arxiv.org/abs/2011.09553

（12）Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking

（13）Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training

https://arxiv.org/abs/2105.15171

（14）Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

https://arxiv.org/abs/2105.14313

（15）RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems

https://arxiv.org/abs/2012.14666

（16）Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

（17）Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances https://arxiv.org/abs/2106.02227

（18）Semantic Representation for Dialogue Modeling

https://arxiv.org/abs/2105.10188

（19）Towards Emotional Support Dialog Systems

https://arxiv.org/abs/2106.01144

（20）Discovering Dialogue Slots with Weak Supervision

（21）Structural Pre-training for Dialogue Comprehension

https://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 Dialog

https://arxiv.org/abs/2106.04571

（25）Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

（26）GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling

https://arxiv.org/abs/2106.01925

（27）DynaEval: Unifying Turn and Dialogue Level Evaluation

https://arxiv.org/abs/2106.01112

Short

（28）Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries

https://arxiv.org/abs/2012.01873

（29）Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking

https://arxiv.org/abs/2106.00291

（30）Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking

（31）Domain-Adaptive Pretraining Methods for Dialogue Understanding

https://arxiv.org/abs/2105.13665

（32）PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation

https://arxiv.org/abs/2004.13835

八、 情感或情绪分析
Long

（1）Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis

（2）Directed Acyclic Graph Network for Conversational Emotion Recognition

https://arxiv.org/abs/2105.12907

（3）DynaSent: A Dynamic Benchmark for Sentiment Analysis

https://arxiv.org/abs/2012.15349

（4）Position Bias Mitigation: A Knowledge-Aware Graph Model for Emotion Cause Extraction

https://arxiv.org/abs/2106.03518

（5）Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection

https://arxiv.org/abs/2106.01071

（6）Distributed Representations of Emotion Categories in Emotion Space

（7）DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations

https://arxiv.org/abs/2106.01978

（8）Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities

（9）A Unified Generative Framework for Aspect-based Sentiment Analysis

https://arxiv.org/abs/2106.04300

（10）Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis

（11）Structured Sentiment Analysis as Dependency Graph Parsing

https://arxiv.org/abs/2105.14504

（12）Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions

Short

（13）Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis

https://arxiv.org/abs/2106.03806

（14）Towards Generative Aspect-Based Sentiment Analysis

（15）eMLM: A New Pre-training Objective for Emotion Related Tasks

九、 信息抽取
Long

（1）Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

https://arxiv.org/abs/2106.08977

（2）Competence-based Multimodal Curriculum Learning for Medical Report Generation

https://arxiv.org/abs/2105.06804

（3）OntoED: Low-resource Event Detection with Ontology Embedding

https://arxiv.org/abs/2105.10922

（4）Subsequence Based Deep Active Learning for Named Entity Recognition

（5）BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition

https://arxiv.org/abs/2105.12848

（6）Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

（7）Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker

https://arxiv.org/abs/2105.14924

（8）A Large-Scale Chinese Multimodal NER Dataset with Speech Clues

（9）LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification

https://arxiv.org/abs/2106.01649

（10）CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction

https://arxiv.org/abs/2106.10855

（11）Few-NERD: A Few-shot Named Entity Recognition Dataset

https://arxiv.org/abs/2105.07464

（12）SENT: Sentence-level Distant Relation Extraction via Negative Training

https://arxiv.org/abs/2106.11566?context=cs

（13）Modularized Interaction Network for Named Entity Recognition

（14）Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder

（15）A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition

（16）An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization

（17）MLBiNet: A Cross-Sentence Collective Event Detection Network

https://arxiv.org/abs/2105.09458

（18）PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction

https://arxiv.org/abs/2106.09895

（20）Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

https://arxiv.org/abs/2105.03654

（21）Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification

（22）Revisiting the Negative Data of Distantly Supervised Relation Extraction

https://arxiv.org/abs/2105.10158

（23）Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition

（24）Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference

https://arxiv.org/abs/2105.13456

（25）Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path

（27）How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction

（28）From Discourse to Narrative: Knowledge Projection for Event Relation Extraction

https://arxiv.org/abs/2106.08629

（29）Fine-grained Information Extraction from Biomedical Literature based on Knowledge-enriched Abstract Meaning Representation

（30）A Unified Generative Framework for Various NER Subtasks

https://arxiv.org/abs/2106.01223

（31）MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition

（32）Unleash GPT-2 Power for Event Detection

（33）Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction

（34）Element Intervention for Open Relation Extraction

https://arxiv.org/abs/2106.09558

（35）Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

https://arxiv.org/abs/2106.09232

（36）CLEVE: Contrastive Pre-training for Event Extraction

https://arxiv.org/abs/2105.14485

（37）MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER

https://raihanjoty.github.io/papers/linlin-et-al-acl-21.html

（38）De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention

https://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 Named Entity Recognition

https://arxiv.org/abs/2105.14980

（41）Modeling Fine-Grained Entity Types with Box Embeddings

https://arxiv.org/abs/2101.00345

（42）CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction

https://arxiv.org/abs/2106.00793

（43）CitationIE: Leveraging the Citation Graph for Scientific Information Extraction

https://arxiv.org/abs/2106.01560

（44）Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks

（45）Discontinuous Named Entity Recognition as Maximal Clique Discovery

https://arxiv.org/abs/2106.00218

（46）Weakly Supervised Named Entity Tagging with Learnable Logical Rules

（47）SpanNER: Named Entity Re-/Recognition as Span Prediction

https://arxiv.org/abs/2106.00641

（48）Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

https://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 Triplet Extraction

（51）The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing

https://arxiv.org/abs/2106.08037

（52）A Neural Transition-based Joint Model for Disease Named Entity Recognition and Normalization

Short

（53）TIMERS: Document-level Temporal Relation Extraction

（54）ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction

https://arxiv.org/abs/2106.10786

（55）Enhancing Entity Boundary Detection for Better Chinese Named Entity Recognition

（56）Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain

（57）Entity Concept-enhanced Few-shot Relation Extraction

https://arxiv.org/abs/2106.02401

（58）Improving Model Generalization: A Chinese Named Entity Recognition Case Study

（59）Explicitly Capturing Relations between Entity Mentions via Graph Neural Networks for Domain-specific Named Entity Recognition

（60）Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction

https://arxiv.org/abs/2106.01793

十、 其他
（1）Semi-Supervised Text Classification with Balanced Deep Representation Distributions

（2）Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble

https://arxiv.org/abs/2006.11627

（3）Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning

https://arxiv.org/abs/2105.04165

（4）Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification

https://arxiv.org/abs/2105.02657

（5）Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification

（6）Joint Verification and Reranking for Open Fact Checking Over Tables

https://arxiv.org/abs/2012.15115

（7）Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor

https://arxiv.org/abs/2010.05010

（8）UnNatural Language Inference

https://arxiv.org/abs/2101.00010

（9）OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification

https://arxiv.org/abs/2105.06750

（10）Database Reasoning Over Text

https://arxiv.org/abs/2106.01074

（11）Towards Robustness of Text-to-SQL Models against Synonym Substitution

https://arxiv.org/abs/2106.01065

（12）Determinantal Beam Search

https://arxiv.org/abs/2106.07400

（13）POS-Constrained Parallel Decoding for Non-autoregressive Generation

（14）Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification

（15）Multi-View Cross-Lingual Structured Prediction with Minimum Supervision

http://faculty.sist.shanghaitech.edu.cn/faculty/tukw/acl21mv.pdf

（16）Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL

（17）Factoring Statutory Reasoning as Language Understanding Challenges

https://arxiv.org/abs/2105.07903

（18）HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization

https://arxiv.org/abs/2106.00149

（19）KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers

https://arxiv.org/abs/2106.11455

（20）Automatic ICD Coding via Interactive Shared Representation Networks with Self-distillation Mechanism

（21）Alignment Rationale for Natural Language Inference