Entity-Relation Extraction as Full Shallow Semantic Dependency Parsing
- 9 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 1088-1099
Abstract
Entity-relation extraction is the essential information extraction task and can be decomposed into Named Entity Recognition (NER) and Relation Extraction (RE) subtasks. This paper proposes a novel joint entity-relation extraction method that models the entity-relation extraction task as full shallow semantic dependency graph parsing. Specifically, it jointly and simultaneously converts the entities and relation mentions as the edges of the semantic dependency graph to be parsed and their types as the labels. This model also integrates the advantages of multiple feature tagging methods and enriches the token representation. Furthermore, second-order scoring is introduced to exploit the relationships between entities and relations, which improves the model performance. Our work is the first time to fully model entities and relations into a graph and uses higher-order modules to address their interaction problems. Compared with state-of-the-art scores on five benchmarks (ACE04, ACE05, CoNLL04, ADE, and SciERC), empirical results show that our proposed model makes significant improvements and demonstrates its effectiveness and practicability.Keywords
Funding Information
- National Natural Science Foundation of China (61976120, 62371261, 62306216)
- Natural Science Foundation of Jiangsu Province (BK20231337)
- Natural Science Key Foundation of Higher Education of Jiangsu Province (21KJA510004)
- General Program of the Natural Science Research of Higher Education of Jiangsu Province (23KJB520031)
- Natural Science Foundation of Hubei Province of China (2023AFB816)
- Joint Research Project of Yangtze River Delta Science and Technology Innovation Community (2022CSJGG1400)
This publication has 49 references indexed in Scilit:
- Representation iterative fusion based on heterogeneous graph neural network for joint entity and relation extractionKnowledge-Based Systems, 2021
- UniRE: A Unified Label Space for Entity Relation Extraction2021
- Relation Extraction with Convolutional Network over Learnable Syntax-Transport GraphProceedings of the AAAI Conference on Artificial Intelligence, 2020
- High-order Semantic Role Labeling2020
- Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders2020
- A Joint Neural Model for Information Extraction with Global Features2020
- End-to-End Neural Relation Extraction Using Deep Biaffine Attention2019
- Joint entity recognition and relation extraction as a multi-head selection problemExpert Systems with Applications, 2018
- Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reportsJournal of Biomedical Informatics, 2012
- Long Short-Term MemoryNeural Computation, 1997