K-SRL: Instance-based Learning for Semantic Role Labeling

Alan Akbik, Yunyao Li


Abstract
Semantic role labeling (SRL) is the task of identifying and labeling predicate-argument structures in sentences with semantic frame and role labels. A known challenge in SRL is the large number of low-frequency exceptions in training data, which are highly context-specific and difficult to generalize. To overcome this challenge, we propose the use of instance-based learning that performs no explicit generalization, but rather extrapolates predictions from the most similar instances in the training data. We present a variant of k-nearest neighbors (kNN) classification with composite features to identify nearest neighbors for SRL. We show that high-quality predictions can be derived from a very small number of similar instances. In a comparative evaluation we experimentally demonstrate that our instance-based learning approach significantly outperforms current state-of-the-art systems on both in-domain and out-of-domain data, reaching F1-scores of 89,28% and 79.91% respectively.
Anthology ID:
C16-1058
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:
599–608
Language:
URL:
https://aclanthology.org/C16-1058
DOI:
Bibkey:
Cite (ACL):
Alan Akbik and Yunyao Li. 2016. K-SRL: Instance-based Learning for Semantic Role Labeling. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 599–608, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
K-SRL: Instance-based Learning for Semantic Role Labeling (Akbik & Li, COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1058.pdf