Attending to Characters in Neural Sequence Labeling Models

Marek Rei, Gamal Crichton, Sampo Pyysalo


Abstract
Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations. By using an attention mechanism, the model is able to dynamically decide how much information to use from a word- or character-level component. We evaluated different architectures on a range of sequence labeling datasets, and character-level extensions were found to improve performance on every benchmark. In addition, the proposed attention-based architecture delivered the best results even with a smaller number of trainable parameters.
Anthology ID:
C16-1030
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
309–318
Language:
URL:
https://aclanthology.org/C16-1030
DOI:
Bibkey:
Cite (ACL):
Marek Rei, Gamal Crichton, and Sampo Pyysalo. 2016. Attending to Characters in Neural Sequence Labeling Models. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 309–318, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Attending to Characters in Neural Sequence Labeling Models (Rei et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/C16-1030.pdf
Data
FCEPenn Treebank