Output details
11 - Computer Science and Informatics
University of Edinburgh
Article title
Semi-Supervised Semantic Role Labeling via Structural Alignment
Type
D - Journal article
Title of journal
Computational Linguistics
Article number
-
Volume number
38
Issue number
1
First page of article
135
ISSN of journal
0891-2017
Year of publication
2011
Number of additional authors
1
Additional information
<22> Originality: First approach to use semi-supervised learning for semantic role labeling.
Significance: The paper shows that it is possible to reduce the manual effort needed for training semantic role labelers using semi-supervised methods which can be used for resource-poor languages. Introduces a framework for semi-supervised learning applicable to several tasks (e.g., paraphrase acquisition).
Rigour: Provides experimental results across several languages and data sets.
Interdisciplinary
-
Cross-referral requested
-
Research group
D - Institute for Language, Cognition & Computation
Citation count
2
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
