Better Feature Integration for Named Entity Recognition

Lu Xu, Zhanming Jie, Wei Lu, Lidong Bing


Abstract
It has been shown that named entity recognition (NER) could benefit from incorporating the long-distance structured information captured by dependency trees. We believe this is because both types of features - the contextual information captured by the linear sequences and the structured information captured by the dependency trees may complement each other. However, existing approaches largely focused on stacking the LSTM and graph neural networks such as graph convolutional networks (GCNs) for building improved NER models, where the exact interaction mechanism between the two types of features is not very clear, and the performance gain does not appear to be significant. In this work, we propose a simple and robust solution to incorporate both types of features with our Synergized-LSTM (Syn-LSTM), which clearly captures how the two types of features interact. We conduct extensive experiments on several standard datasets across four languages. The results demonstrate that the proposed model achieves better performance than previous approaches while requiring fewer parameters. Our further analysis demonstrates that our model can capture longer dependencies compared with strong baselines.
Anthology ID:
2021.naacl-main.271
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3457–3469
Language:
URL:
https://aclanthology.org/2021.naacl-main.271
DOI:
10.18653/v1/2021.naacl-main.271
Bibkey:
Cite (ACL):
Lu Xu, Zhanming Jie, Wei Lu, and Lidong Bing. 2021. Better Feature Integration for Named Entity Recognition. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3457–3469, Online. Association for Computational Linguistics.
Cite (Informal):
Better Feature Integration for Named Entity Recognition (Xu et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.271.pdf
Video:
 https://aclanthology.org/2021.naacl-main.271.mp4
Code
 xuuuluuu/SynLSTM-for-NER
Data
OntoNotes 5.0