Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
arXiv:1809.09078 · doi:10.18653/v1/D18-1156
Abstract
Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single event. Previous works on modeling the associations between events by sequential modeling methods suffer a lot from the low efficiency in capturing very long-range dependencies. In this paper, we propose a novel Jointly Multiple Events Extraction (JMEE) framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. The experiment results demonstrate that our proposed framework achieves competitive results compared with state-of-the-art methods.
accepted by EMNLP 2018
References in corpus (2)
Cited by in corpus (38)
- Graph Neural Networks: A Review of Methods and Applications
- Graph Neural Networks: Taxonomy, Advances and Trends
- Dynamic Prefix-Tuning for Generative Template-based Event Extraction
- Graph Neural Networks for Natural Language Processing: A Survey
- Ontology-enhanced Prompt-tuning for Few-shot Learning
- Open Domain Event Extraction Using Neural Latent Variable Models
- Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks
- Event Extraction by Answering (Almost) Natural Questions
- Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction
- Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networks
- OntoED: Low-resource Event Detection with Ontology Embedding
- Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks
- Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
- Cross-media Structured Common Space for Multimedia Event Extraction
- QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval
- Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker
- Enhancing Event-Level Sentiment Analysis with Structured Arguments
- MAVEN: A Massive General Domain Event Detection Dataset
- Incorporating Fine-grained Events in Stock Movement Prediction
- Label Enhanced Event Detection with Heterogeneous Graph Attention Networks
- MLBiNet: A Cross-Sentence Collective Event Detection Network
- Biomedical Event Extraction with Hierarchical Knowledge Graphs
- Event Detection as Question Answering with Entity Information
- Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
- CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction
- Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference
- GRIT: Generative Role-filler Transformers for Document-level Event Entity Extraction
- An overview of event extraction and its applications
- Document-level Event Extraction with Efficient End-to-end Learning of Cross-event Dependencies
- Comprehensive Event Representations using Event Knowledge Graphs and Natural Language Processing
- Cost-sensitive Regularization for Label Confusion-aware Event Detection
- Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
- Resource-Enhanced Neural Model for Event Argument Extraction
- GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition
- Enhanced Language Representation with Label Knowledge for Span Extraction
- Effective Use of Graph Convolution Network and Contextual Sub-Tree forCommodity News Event Extraction
- Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding
- Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain