EMNLP2020中事件抽取/关系抽取/NER/少样本/MRC/摘要 论文分类整理

**EMNLP2020放榜啦！**小编根据个人研究方向相关将主会和Findings论文进行了一些分类整理，(●’◡’●)整理中如有错误与疏漏，还请大家多多交流指正嗷！

主会论文榜单传送门: https://2020.emnlp.org/papers/main

Findings论文榜单传送门: https://2020.emnlp.org/papers/findings

ps.此文也在知乎发布啦！欢迎在知乎关注我: Carrie

事件抽取

主会

• Affective Event Classification with Discourse-enhanced Self-training

• Biomedical Event Extraction as Sequence Labeling

• Connecting the Dots: Event Graph Schema Induction with Path Language Modeling

• Event Extraction as Machine Reading Comprehension

• Event Extraction by Answering (Almost) Natural Questions

• Incremental Event Detection via Knowledge Consolidation Networks

• MAVEN: A Massive General Domain Event Detection Dataset

• Weakly Supervised Subevent Knowledge Acquisition

• Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks

• Introducing a New Dataset for Event Detection in Cybersecurity Texts

• Semi-supervised New Event Type Induction and Event Detection

Findings

• Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation

• Event Extraction as Multi-turn Question Answering

• How Does Context Matter? On the Robustness of Event Detection with Context-Selective Mask Generalization

• Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction

• Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs

• Resource-Enhanced Neural Model for Event Argument Extraction

• Learning to Classify Events from Human Needs Category Descriptions

关系抽取

主会

• Double Graph Based Reasoning for Document-level Relation Extraction

• FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction

• Global-to-Local Neural Networks for Document-Level Relation Extraction

• Learning from Context or Names? An Empirical Study on Neural Relation Extraction

• Let’s Stop Error Propagation in the End-to-End Relation Extraction Literature!

• Pre-training Entity Relation Encoder with Intra-span and Inter-span Information

• Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations

• Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations

• SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction

• Two are Better Than One: Joint Entity and Relation Extraction with Table-Sequence Encoders

• Denoising Relation Extraction from Document-level Distant Supervision

• Distilling Structured Knowledge for Text-Based Relational Reasoning

• Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data

• Joint Constrained Learning for Event-Event Relation Extraction

• Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction. Rujun Han, Yichao Zhou and Nanyun Peng

Findings

• Active Testing: An Unbiased Evaluation Method for Distantly Supervised Relation Extraction

• Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction

• The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification

• Unsupervised Relation Extraction from Language Models using Constrained Cloze Completion

• The Dots Have Their Values: Exploiting the Node-Edge Connections in Graph-based Neural Models for Document-level Relation Extraction

NER

主会

• Coarse-to-Fine Pre-training for Named Entity Recognition

• A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?

• Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

• Entity Enhanced BERT Pre-training for Chinese NER

• Frustratingly Simple Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

• HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction

• Interpretable Multi-dataset Evaluation for Named Entity Recognition

• Named Entity Recognition Only from Word Embeddings

• Named Entity Recognition for Social Media Texts with Semantic Augmentatio

Findings

• Toward Recognizing More Entity Types in NER: An Efficient Implementation using Only Entity Lexicons

• A Dual-Attention Network for Joint Named Entity Recognition and Sentence Classification of Adverse Drug Events

• Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information

• Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers

• Hierarchical Region Learning for Nested Named Entity Recognition

FewShot & ZeroShot

主会

• Adaptive Attentional Network for Few-Shot Knowledge Graph Completion

• An Empirical Study on Large-Scale Multi-Label Text Classification including Few and Zero-Shot Labels

• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference

• Few-shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

• Few-Shot Learning for Opinion Summarization

• Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks

• Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models

• Frustratingly Simple Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

• Scalable Zero-shot Entity Linking with Dense Entity RetrievalScalable Zero-shot Entity Linking with Dense Entity Retrieval

• Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start

• Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs

• Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing

• From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers

• Grounded Adaptation for Zero-shot Executable Semantic Parsing

• MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale

• Scalable Zero-shot Entity Linking with Dense Entity Retrieval

• Self-Supervised Knowledge Triplet Learning for Zero-shot Question Answering

• Zero-Shot Cross-Lingual Transfer with Meta Learning

• Zero-Shot Crosslingual Sentence Simplification

• Language Adapters for Zero Shot Neural Machine Translation

• On the Evaluation of Contextual Embeddings for Zero-Shot Cross-Lingual Transfer Learning

• SLEDGE: A Simple Yet Effective Zero-Shot Baseline for Coronavirus Scientific Knowledge Search

Findings

• Few-shot Natural Language Generation for Task-Oriented Dialog

• Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases

• Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection

• Composed Variational Natural Language Generation for Few-shot Intents

• Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation

• Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases

• Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines

• Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection

• Zero-shot Entity Linking with Efficient Long Range Sequence Modeling

• ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization

• Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering

• Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning

• Sparse and Decorrelated Representations for Stable Zero-shot NMT

• Zero-shot Entity Linking with Efficient Long Range Sequence Modeling

MRC & QA

主会

• Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering

• Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading

• IIRC: A Dataset of Incomplete Information Reading Comprehension Questions

• Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning

• MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics

• Scene Restoring for Narrative Machine Reading Comprehension

• TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions

• Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text

• Reading Between the Lines: Exploring Infilling in Visual Narratives

• Towards Interpreting BERT for Reading Comprehension Based QA

• Neural Conversational QA: Learning to Reason vs Exploiting Patterns

• A Simple Yet Strong Pipeline for HotpotQA

• SubjQA: A Dataset for Subjectivity and Review Comprehension

• STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering

• QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines

• ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning

• LAReQA: Language-agnostic answer retrieval from a multilingual pool

• Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning

• AutoQA: From Databases To Q&A Semantic Parsers With Only Synthetic Training Data

• AmbigQA: Answering Ambiguous Open-domain Questions

• Hierarchical Graph Network for Multi-hop Question Answering

• Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering

• Is Graph Structure Necessary for Multi-hop Question Answering?

Findings

• Undersensitivity in Neural Reading Comprehension

• Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension

• No Answer is Better Than Wrong Answer: A Reflection Model for Document Level Machine Reading Comprehension

• PolicyQA: A Reading Comprehension Dataset for Privacy Policies

• Answer Span Correction in Machine Reading Comprehension

• Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation

• ConceptBert: Concept-Aware Representation for Visual Question Answering

• HybridQA: A Dataset of Multi-Hop Question Answering

• FQuAD: French Question Answering Dataset

• Question Answering with Long Multiple-Span Answers

• Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

• Multi-hop Question Generation with Graph Convolutional Network

• MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering

• Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyperedge Infusion

Summarization

• A Spectral Method for Unsupervised Multi-Document Summarization

• Coarse-to-Fine Query Focused Multi-Document Summarization

• Compressive Summarization with Plausibility and Salience Modeling

• Evaluating the Factual Consistency of Abstractive Text Summarization

• Friendly Topic Assistant for Transformer Based Abstractive Summarization

• Intrinsic Evaluation of Summarization Datasets

• MLSUM: The Multilingual Summarization Corpus

• Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning

• Multi-Fact Correction in Abstractive Text Summarization

• Multi-hop Inference for Question-driven Summarization

• Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization

• Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network

• On Extractive and Abstractive Neural Document Summarization with Transformer Language Models

• Pre-training for Abstractive Document Summarization by Reinstating Source Text

• Q-learning with Language Model for Edit-based Unsupervised Summarization

• Re-evaluating Evaluation in Text Summarization

• Stepwise Extractive Summarization and Planning with Structured Transformers

• TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization

• What Have We Achieved on Text Summarization?

• Factual Error Correction for Abstractive Summarization Models

• Learning to Fuse Sentences with Transformers for Summarization

• Modeling Content Importance for Summarization with Pre-trained Language Models

• Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles

• Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach

• Understanding Neural Abstractive Summarization Models via Uncertainty

Findings

• A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining

• Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization

• Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers

• TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising

• Reducing Quantity Hallucinations in Abstractive Summarization

• Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization

• Corpora Evaluation and System Bias Detection in Multi-document Summarization

• Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning

• Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization

• CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems

• Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures

• WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization

• SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy

• TLDR: Extreme Summarization of Scientific Documents

Others

主会

• QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines

• Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

• Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph

• Multi-hop Inference for Question-driven Summarization

---

了解更多深度学习相关知识与信息，请关注公众号深度学习的知识小屋