Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media

Bill Y. Lin, Frank Xu, Zhiyi Luo, Kenny Zhu


Abstract
In this paper, we present our multi-channel neural architecture for recognizing emerging named entity in social media messages, which we applied in the Novel and Emerging Named Entity Recognition shared task at the EMNLP 2017 Workshop on Noisy User-generated Text (W-NUT). We propose a novel approach, which incorporates comprehensive word representations with multi-channel information and Conditional Random Fields (CRF) into a traditional Bidirectional Long Short-Term Memory (BiLSTM) neural network without using any additional hand-craft features such as gazetteers. In comparison with other systems participating in the shared task, our system won the 2nd place.
Anthology ID:
W17-4421
Volume:
Proceedings of the 3rd Workshop on Noisy User-generated Text
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Leon Derczynski, Wei Xu, Alan Ritter, Tim Baldwin
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
160–165
Language:
URL:
https://aclanthology.org/W17-4421
DOI:
10.18653/v1/W17-4421
Bibkey:
Cite (ACL):
Bill Y. Lin, Frank Xu, Zhiyi Luo, and Kenny Zhu. 2017. Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media. In Proceedings of the 3rd Workshop on Noisy User-generated Text, pages 160–165, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media (Lin et al., WNUT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-4421.pdf
Data
IPM NEL