Semantic Tagging with Deep Residual Networks

Johannes Bjerva, Barbara Plank, Johan Bos


Abstract
We propose a novel semantic tagging task, semtagging, tailored for the purpose of multilingual semantic parsing, and present the first tagger using deep residual networks (ResNets). Our tagger uses both word and character representations, and includes a novel residual bypass architecture. We evaluate the tagset both intrinsically on the new task of semantic tagging, as well as on Part-of-Speech (POS) tagging. Our system, consisting of a ResNet and an auxiliary loss function predicting our semantic tags, significantly outperforms prior results on English Universal Dependencies POS tagging (95.71% accuracy on UD v1.2 and 95.67% accuracy on UD v1.3).
Anthology ID:
C16-1333
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:
3531–3541
Language:
URL:
https://aclanthology.org/C16-1333
DOI:
Bibkey:
Cite (ACL):
Johannes Bjerva, Barbara Plank, and Johan Bos. 2016. Semantic Tagging with Deep Residual Networks. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3531–3541, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Semantic Tagging with Deep Residual Networks (Bjerva et al., COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1333.pdf
Code
 bjerva/semantic-tagging
Data
Groningen Meaning BankUniversal Dependencies