Robust Lexical Features for Improved Neural Network Named-Entity Recognition

Abbas Ghaddar, Phillippe Langlais


Abstract
Neural network approaches to Named-Entity Recognition reduce the need for carefully hand-crafted features. While some features do remain in state-of-the-art systems, lexical features have been mostly discarded, with the exception of gazetteers. In this work, we show that this is unfair: lexical features are actually quite useful. We propose to embed words and entity types into a low-dimensional vector space we train from annotated data produced by distant supervision thanks to Wikipedia. From this, we compute — offline — a feature vector representing each word. When used with a vanilla recurrent neural network model, this representation yields substantial improvements. We establish a new state-of-the-art F1 score of 87.95 on ONTONOTES 5.0, while matching state-of-the-art performance with a F1 score of 91.73 on the over-studied CONLL-2003 dataset.
Anthology ID:
C18-1161
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1896–1907
Language:
URL:
https://aclanthology.org/C18-1161
DOI:
Bibkey:
Cite (ACL):
Abbas Ghaddar and Phillippe Langlais. 2018. Robust Lexical Features for Improved Neural Network Named-Entity Recognition. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1896–1907, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Robust Lexical Features for Improved Neural Network Named-Entity Recognition (Ghaddar & Langlais, COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1161.pdf
Data
CoNLLCoNLL 2003DBpediaOntoNotes 5.0