ACL2021 | 信息抽取相关论文

一、实体抽取

“

实体抽取主要涉及嵌套NER、非连续NER、中文&多模NER、少样本NER、实体标准化、实体分类等；

嵌套&非连续NER

1. A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition
2. Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition
3. Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path
4. Discontinuous Named Entity Recognition as Maximal Clique Discovery
5. A Unified Generative Framework for Various NER Subtasks

少样本NER

1. Subsequence Based Deep Active Learning for Named Entity Recognition
2. Few-NERD: A Few-shot Named Entity Recognition Dataset
3. Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data
4. Weakly Supervised Named Entity Tagging with Learnable Logical Rules
5. Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification
6. Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition

中文&多模NER

1. MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition
2. A Large-Scale Chinese Multimodal NER Dataset with Speech Clues

实体标准化

1. An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization
2. A Neural Transition-based Joint Model for Disease Named Entity Recognition and Normalization

实体分类

1. Modeling Fine-Grained Entity Types with Box Embeddings
2. Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model

其他

1. SpanNER: Named Entity Re-/Recognition as Span Prediction
2. Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
3. Modularized Interaction Network for Named Entity Recognition
4. BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition
5. De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention
6. Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
7. LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking

二、关系抽取

“

关系抽取主要涉及远程监督抽取、联合抽取、开放抽取、事件关系抽取等。

远程监督

1. CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
2. How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction
3. SENT: Sentence-level Distant Relation Extraction via Negative Training
4. Revisiting the Negative Data of Distantly Supervised Relation Extraction

联合抽取

1. Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference
2. UniRE: A Unified Label Space for Entity Relation Extraction
3. PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
4. Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks

开放抽取

1. CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction
2. Element Intervention for Open Relation Extraction

事件关系抽取

1. From Discourse to Narrative: Knowledge Projection for Event Relation Extraction

其他

1. Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction

三、事件抽取

1. Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
2. Verb Knowledge Injection for Multilingual Event Processing
3. OntoED: Low-resource Event Detection with Ontology Embedding
4. Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker
5. LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification
6. MLBiNet: A Cross-Sentence Collective Event Detection Network
7. Unleash GPT-2 Power for Event Detection
8. Document-Level Event Argument Extraction via Optimal
9. Document-level Event Extraction via Parallel Prediction Networks
10. Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction
11. The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing
12. Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

四、信息抽取预训练

1. ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning
2. CLEVE: Contrastive Pre-training for Event Extraction