A Prism Module for Semantic Disentanglement in Name Entity Recognition

Kun Liu, Shen Li, Daqi Zheng, Zhengdong Lu, Sheng Gao, Si Li


Abstract
Natural Language Processing has been perplexed for many years by the problem that multiple semantics are mixed inside a word, even with the help of context. To solve this problem, we propose a prism module to disentangle the semantic aspects of words and reduce noise at the input layer of a model. In the prism module, some words are selectively replaced with task-related semantic aspects, then these denoised word representations can be fed into downstream tasks to make them easier. Besides, we also introduce a structure to train this module jointly with the downstream model without additional data. This module can be easily integrated into the downstream model and significantly improve the performance of baselines on named entity recognition (NER) task. The ablation analysis demonstrates the rationality of the method. As a side effect, the proposed method also provides a way to visualize the contribution of each word.
Anthology ID:
P19-1532
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5358–5362
Language:
URL:
https://aclanthology.org/P19-1532
DOI:
10.18653/v1/P19-1532
Bibkey:
Cite (ACL):
Kun Liu, Shen Li, Daqi Zheng, Zhengdong Lu, Sheng Gao, and Si Li. 2019. A Prism Module for Semantic Disentanglement in Name Entity Recognition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5358–5362, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
A Prism Module for Semantic Disentanglement in Name Entity Recognition (Liu et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1532.pdf
Data
CoNLLCoNLL 2003