NAACL2021 信息抽取与少/零样本相关论文整理

NAACL2021放榜啦！！具体情况这里！

小编对其中 事件抽取、关系抽取、NER和Few-Shot / Zero-Shot相关的论文整理如下，欢迎补充整理呦:

事件抽取

• WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia

• Event Representation with Sequential, Semi-Supervised Discrete Variables

• Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures

• Modeling Event Plausibility with Consistent Conceptual Abstraction

• Constrained Learning for End-to-End Event Reference Interpretation

• Document-Level Event Argument Extraction by Conditional Generation

• A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution

• Event Time Extraction and Propagation via Graph Attention Networks

• Temporal Reasoning on Implicit Events from Distant Supervision

• RESIN: A Dockerlized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System

• EventPlus: A Temporal Event Understanding Pipeline

关系抽取

• Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction

• Open Hierarchical Relation Extraction

• Towards Zero-Shot Relation Extraction with Attribute Representation Learning

• A Frustratingly Easy Approach for Entity and Relation Extraction

• Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors

NER

• Noisy-Labeled NER with Confidence Estimation

• COVID-19 named entity recognition for Vietnamese

• Multi-Grained Knowledge Distillation for Named Entity Recognition

• Fusing Structured Information into LSTM for Named Entity Recognition

• (Demo)PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing

Few-Shot/Zero-Shot

• Knowledge Guided Metric Learning for Few-Shot Text Classification

• It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners

• Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation

• Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning

• Non-parametric Few-Shot Learning for Word Sense Disambiguation

• Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

• Towards Few-shot Fact-Checking via Perplexity

• DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference

• ConVEx: Data-Efficient and Few-Shot Slot Labeling

• Few-shot Intent Classification and Slot Filling with Retrieved Examples

• Adversarial Learning for Zero-Shot Stance Detection on Social Media

• Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning

• Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling

• From Masked-Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding

• Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models

• Revisiting Document Representations for Large-Scale Zero-Shot Learning

• Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph

• Towards Zero-Shot Relation Extraction with Attribute Representation Learning

• Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking