Advanced

A Distant Supervision Approach to Semantic Role Labeling

Exner, Peter LU ; Klang, Marcus LU and Nugues, Pierre LU (2015) Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015) In Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015) p.239-248
Abstract
Semanticrolelabelinghasbecomeakeymodule for many language processing applications such as question answering, information extraction, sentiment analysis, and machine translation. To build an unrestricted semantic role labeler, the first step is to develop a comprehensive proposition bank. However, creating such a bank is a costly enterprise, which has only been achieved for a handful of languages. In this paper, we describe a technique to build proposition banks for new languages using distant supervision. Starting from PropBank inEnglishandlooselyparallelcorporasuchas versions of Wikipedia in different languages, we carried out a mapping of semantic propositions we extracted from English to syntactic structures in Swedish using named... (More)
Semanticrolelabelinghasbecomeakeymodule for many language processing applications such as question answering, information extraction, sentiment analysis, and machine translation. To build an unrestricted semantic role labeler, the first step is to develop a comprehensive proposition bank. However, creating such a bank is a costly enterprise, which has only been achieved for a handful of languages. In this paper, we describe a technique to build proposition banks for new languages using distant supervision. Starting from PropBank inEnglishandlooselyparallelcorporasuchas versions of Wikipedia in different languages, we carried out a mapping of semantic propositions we extracted from English to syntactic structures in Swedish using named entities. We trained a semantic parser on the generated Swedishpropositionsandwereporttheresults we obtained. Using the CoNLL 2009 evaluation script, we could reach the scores of 52.25 for labeled propositions and 62.44 for the unlabeled ones. We believe our approach can be appliedtotrainsemanticrolelabelersforother resource-scarce languages.
(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015)
pages
239 - 248
conference name
Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015)
language
English
LU publication?
yes
id
169e2f54-f36a-4e09-8860-870fbcb06ac3 (old id 5469382)
date added to LUP
2015-06-10 16:04:30
date last changed
2017-01-12 12:04:02
@inproceedings{169e2f54-f36a-4e09-8860-870fbcb06ac3,
  abstract     = {Semanticrolelabelinghasbecomeakeymodule for many language processing applications such as question answering, information extraction, sentiment analysis, and machine translation. To build an unrestricted semantic role labeler, the first step is to develop a comprehensive proposition bank. However, creating such a bank is a costly enterprise, which has only been achieved for a handful of languages. In this paper, we describe a technique to build proposition banks for new languages using distant supervision. Starting from PropBank inEnglishandlooselyparallelcorporasuchas versions of Wikipedia in different languages, we carried out a mapping of semantic propositions we extracted from English to syntactic structures in Swedish using named entities. We trained a semantic parser on the generated Swedishpropositionsandwereporttheresults we obtained. Using the CoNLL 2009 evaluation script, we could reach the scores of 52.25 for labeled propositions and 62.44 for the unlabeled ones. We believe our approach can be appliedtotrainsemanticrolelabelersforother resource-scarce languages.<br/>},
  author       = {Exner, Peter and Klang, Marcus and Nugues, Pierre},
  booktitle    = {Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015)},
  language     = {eng},
  pages        = {239--248},
  title        = {A Distant Supervision Approach to Semantic Role Labeling},
  year         = {2015},
}