Non-atomic classification to improve a semantic role labeler for a low-resource language

Authors:
Richard Johansson
Affiliations:
Språkbanken, University of Gothenburg, Gothenburg, Sweden
Venue:
SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
Year:
2012

Citing 11
Cited 0

Class-based n-gram models of natural language

Computational Linguistics
Automatic labeling of semantic roles

Computational Linguistics
The Berkeley FrameNet Project

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Online Passive-Aggressive Algorithms

The Journal of Machine Learning Research
Semantic role labeling: an introduction to the special issue

Computational Linguistics
Dependency-based syntactic-semantic analysis with PropBank and NomBank

CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
The effect of syntactic representation on semantic role labeling

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
LTH: semantic structure extraction using nonprojective dependency trees

SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Aspect Guided Text Categorization with Unobserved Labels

ICDM '09 Proceedings of the 2009 Ninth IEEE International Conference on Data Mining
A comparative study on generalization of semantic roles in FrameNet

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Probabilistic frame-semantic parsing

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Semantic role classification accuracy for most languages other than English is constrained by the small amount of annotated data. In this paper, we demonstrate how the frame-to-frame relations described in the FrameNet ontology can be used to improve the performance of a FrameNet-based semantic role classifier for Swedish, a low-resource language. In order to make use of the FrameNet relations, we cast the semantic role classification task as a non-atomic label prediction task. The experiments show that the cross-frame generalization methods lead to a 27% reduction in the number of errors made by the classifier. For previously unseen frames, the reduction is even more significant: 50%.