Multi-Turn and Multi-Granularity Reader for Document-Level Event Extraction
Open Access
- 27 December 2022
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (2) , 1-16
Abstract
Most existing event extraction works mainly focus on extracting events from one sentence. However, in real-world applications, arguments of one event may scatter across sentences and multiple events may co-occur in one document. Thus, these scenarios require document-level event extraction (DEE), which aims to extract events and their arguments across sentences from a document. Previous works cast DEE as a two-step paradigm: sentence-level event extraction (SEE) to document-level event fusion. However, this paradigm lacks integrating document-level information for SEE and suffers from the inherent limitations of error propagation. In this article, we propose a multi-turn and multi-granularity reader for DEE that can extract events from the document directly without the stage of preliminary SEE. Specifically, we propose a new paradigm of DEE by formulating it as a machine reading comprehension task (i.e., the extraction of event arguments is transformed to identify the answer span from the document). Beyond the framework of machine reading comprehension, we introduce a multi-turn and multi-granularity reader to capture the dependencies between arguments explicitly and model long texts effectively. The empirical results demonstrate that our method achieves superior performance on the MUC-4 and the ChFinAnn datasets.Keywords
Funding Information
- National Key Research and Development Program of China (2020AAA0106400)
- National Natural Science Foundation of China (61976211, 61922085, 62176257)
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDA27020200)
- CCF-Tencent Open Research Fund, the Youth Innovation Promotion Association CAS
- Yunnan Provincial Major Science and Technology Special Plan Projects (202103AA080015)
This publication has 25 references indexed in Scilit:
- Biomedical Event Extraction Using Convolutional Neural Networks and Dependency Parsing2018
- DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data2018
- ReasoNet2017
- Zero-Shot Relation Extraction via Reading Comprehension2017
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension2017
- RACE: Large-scale ReAding Comprehension Dataset From Examinations2017
- SQuAD: 100,000+ Questions for Machine Comprehension of Text2016
- Joint Event Extraction via Recurrent Neural Networks2016
- Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks2015
- Modeling Biological Processes for Reading Comprehension2014