Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training

Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens


Abstract
We present a successful collaboration of word embeddings and co-training to tackle in the most difficult test case of semantic role labeling: predicting out-of-domain and unseen semantic frames. Despite the fact that co-training is a successful traditional semi-supervised method, its application in SRL is very limited especially when a huge amount of labeled data is available. In this work, co-training is used together with word embeddings to improve the performance of a system trained on a large training dataset. We also introduce a semantic role labeling system with a simple learning architecture and effective inference that is easily adaptable to semi-supervised settings with new training data and/or new features. On the out-of-domain testing set of the standard benchmark CoNLL 2009 data our simple approach achieves high performance and improves state-of-the-art results.
Anthology ID:
C16-1121
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:
1275–1284
Language:
URL:
https://aclanthology.org/C16-1121
DOI:
Bibkey:
Cite (ACL):
Quynh Ngoc Thi Do, Steven Bethard, and Marie-Francine Moens. 2016. Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1275–1284, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training (Do et al., COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1121.pdf