Joint Constrained Learning for Event-Event Relation Extraction
Preprint
Abstract
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other. In this process, one can induce event complexes that organize multi-granular events with temporal order and membership relations interweaving among them. Due to the lack of jointly labeled data for these relational phenomena and the restriction on the structures they articulate, we propose a joint constrained learning framework for modeling event-event relations. Specifically, the framework enforces logical constraints within and across multiple temporal and subevent relations by converting these constraints into differentiable learning objectives. We show that our joint constrained learning approach effectively compensates for the lack of jointly labeled data, and outperforms SOTA methods on benchmarks for both temporal relation extraction and event hierarchy construction, replacing a commonly used but more expensive global inference process. We also present a promising case study showing the effectiveness of our approach in inducing event complexes on an external corpus.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Mutation effect estimation on protein–protein interactions using deep contextualized representation learningNAR Genomics and Bioinformatics, 2020
- A Joint Neural Model for Information Extraction with Global Features2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- A Logic-Driven Framework for Consistency of Neural Models2019
- Deep Structured Neural Network for Event Temporal Relation Extraction2019
- CogCompTime: A Tool for Understanding Time in Natural Language2018
- A Multi-Axis Annotation Scheme for Event Temporal Relations2018
- Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource2018
- ConceptNet 5.5: An Open Multilingual Graph of General KnowledgeProceedings of the AAAI Conference on Artificial Intelligence, 2017
- A Structured Learning Approach to Temporal Relation Extraction2017