Cross-lingual parse disambiguation based on semantic correspondence

Cross-lingual parse disambiguation based on semantic correspondence

We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that different languages have different ambiguities. We simultaneously reduce ambiguity in multiple languages in a fully automatic wa...

Full description

Saved in:
Bibliographic Details
Main Authors: Frermann, Lea, Bond, Francis
Other Authors: School of Humanities and Social Sciences
Format: Conference or Workshop Item
Language:English
Published: 2013
Online Access:https://hdl.handle.net/10356/97053
http://hdl.handle.net/10220/13067
http://aclweb.org/anthology/P/P12/
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-97053
record_format dspace
spelling sg-ntu-dr.10356-970532019-12-06T19:38:20Z Cross-lingual parse disambiguation based on semantic correspondence Frermann, Lea Bond, Francis School of Humanities and Social Sciences Annual Meeting on Association for Computational Linguistics (50th : 2012) We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that different languages have different ambiguities. We simultaneously reduce ambiguity in multiple languages in a fully automatic way. Evaluation shows that the system reliably discards dispreferred parses from the raw parser output, which results in a pre-selection that can speed up manual treebanking. Published Version 2013-08-12T08:02:52Z 2019-12-06T19:38:20Z 2013-08-12T08:02:52Z 2019-12-06T19:38:20Z 2012 2012 Conference Paper https://hdl.handle.net/10356/97053 http://hdl.handle.net/10220/13067 http://aclweb.org/anthology/P/P12/ en © 2012 Association for Computational Linguistics. This paper was published in Annual Meeting on Association for Computational Linguistics and is made available as an electronic reprint (preprint) with permission of Association for Computational Linguistics. The paper can be found at the following URL: [http://aclweb.org/anthology/P/P12/]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
description We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that different languages have different ambiguities. We simultaneously reduce ambiguity in multiple languages in a fully automatic way. Evaluation shows that the system reliably discards dispreferred parses from the raw parser output, which results in a pre-selection that can speed up manual treebanking.
author2 School of Humanities and Social Sciences
author_facet School of Humanities and Social Sciences
Frermann, Lea
Bond, Francis
format Conference or Workshop Item
author Frermann, Lea
Bond, Francis
spellingShingle Frermann, Lea
Bond, Francis
Cross-lingual parse disambiguation based on semantic correspondence
author_sort Frermann, Lea
title Cross-lingual parse disambiguation based on semantic correspondence
title_short Cross-lingual parse disambiguation based on semantic correspondence
title_full Cross-lingual parse disambiguation based on semantic correspondence
title_fullStr Cross-lingual parse disambiguation based on semantic correspondence
title_full_unstemmed Cross-lingual parse disambiguation based on semantic correspondence
title_sort cross-lingual parse disambiguation based on semantic correspondence
publishDate 2013
url https://hdl.handle.net/10356/97053
http://hdl.handle.net/10220/13067
http://aclweb.org/anthology/P/P12/
_version_ 1681044260030251008

Similar Items