Dependency-Guided LSTM-CRF for Named Entity Recognition

Zhanming Jie, Wei Lu


Abstract
Dependency tree structures capture long-distance and syntactic relationships between words in a sentence. The syntactic relations (e.g., nominal subject, object) can potentially infer the existence of certain named entities. In addition, the performance of a named entity recognizer could benefit from the long-distance dependencies between the words in dependency trees. In this work, we propose a simple yet effective dependency-guided LSTM-CRF model to encode the complete dependency trees and capture the above properties for the task of named entity recognition (NER). The data statistics show strong correlations between the entity types and dependency relations. We conduct extensive experiments on several standard datasets and demonstrate the effectiveness of the proposed model in improving NER and achieving state-of-the-art performance. Our analysis reveals that the significant improvements mainly result from the dependency relations and long-distance interactions provided by dependency trees.
Anthology ID:
D19-1399
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3862–3872
Language:
URL:
https://aclanthology.org/D19-1399
DOI:
10.18653/v1/D19-1399
Bibkey:
Cite (ACL):
Zhanming Jie and Wei Lu. 2019. Dependency-Guided LSTM-CRF for Named Entity Recognition. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3862–3872, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Dependency-Guided LSTM-CRF for Named Entity Recognition (Jie & Lu, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1399.pdf
Attachment:
 D19-1399.Attachment.zip
Code
 allanj/ner_with_dependency
Data
CoNLLCoNLL 2003OntoNotes 5.0