An Empirical Exploration of Skip Connections for Sequential Tagging

Huijia Wu, Jiajun Zhang, Chengqing Zong


Abstract
In this paper, we empirically explore the effects of various kinds of skip connections in stacked bidirectional LSTMs for sequential tagging. We investigate three kinds of skip connections connecting to LSTM cells: (a) skip connections to the gates, (b) skip connections to the internal states and (c) skip connections to the cell outputs. We present comprehensive experiments showing that skip connections to cell outputs outperform the remaining two. Furthermore, we observe that using gated identity functions as skip mappings works pretty well. Based on this novel skip connections, we successfully train deep stacked bidirectional LSTM models and obtain state-of-the-art results on CCG supertagging and comparable results on POS tagging.
Anthology ID:
C16-1020
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
203–212
Language:
URL:
https://aclanthology.org/C16-1020
DOI:
Bibkey:
Cite (ACL):
Huijia Wu, Jiajun Zhang, and Chengqing Zong. 2016. An Empirical Exploration of Skip Connections for Sequential Tagging. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 203–212, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
An Empirical Exploration of Skip Connections for Sequential Tagging (Wu et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/C16-1020.pdf
Data
Penn Treebank