A Joint Neural Model for Information Extraction with Global Features

Ying Lin, Heng Ji, Fei Huang, Lingfei Wu


Abstract
Most existing joint neural models for Information Extraction (IE) use local task-specific classifiers to predict labels for individual instances (e.g., trigger, relation) regardless of their interactions. For example, a victim of a die event is likely to be a victim of an attack event in the same sentence. In order to capture such cross-subtask and cross-instance inter-dependencies, we propose a joint neural framework, OneIE, that aims to extract the globally optimal IE result as a graph from an input sentence. OneIE performs end-to-end IE in four stages: (1) Encoding a given sentence as contextualized word representations; (2) Identifying entity mentions and event triggers as nodes; (3) Computing label scores for all nodes and their pairwise links using local classifiers; (4) Searching for the globally optimal graph with a beam decoder. At the decoding stage, we incorporate global features to capture the cross-subtask and cross-instance interactions. Experiments show that adding global features improves the performance of our model and achieves new state of-the-art on all subtasks. In addition, as OneIE does not use any language-specific feature, we prove it can be easily applied to new languages or trained in a multilingual manner.
Anthology ID:
2020.acl-main.713
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7999–8009
Language:
URL:
https://aclanthology.org/2020.acl-main.713
DOI:
10.18653/v1/2020.acl-main.713
Bibkey:
Cite (ACL):
Ying Lin, Heng Ji, Fei Huang, and Lingfei Wu. 2020. A Joint Neural Model for Information Extraction with Global Features. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7999–8009, Online. Association for Computational Linguistics.
Cite (Informal):
A Joint Neural Model for Information Extraction with Global Features (Lin et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.713.pdf
Video:
 http://slideslive.com/38929257