Alternation-based lexicon reconstruction

This research is aimed at developing a hierarchical alternation-based lexical architecture for machine translation. The proposed architecture makes extensive use of informati...

Full description

Saved in:
Bibliographic Details
Main Authors: Baldwin, Timothy, Bond, Francis
Other Authors: School of Humanities and Social Sciences
Format: Conference or Workshop Item
Language:English
Published: 2010
Subjects:
Online Access:https://hdl.handle.net/10356/92184
http://hdl.handle.net/10220/6437
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-92184
record_format dspace
spelling sg-ntu-dr.10356-921842019-12-06T18:18:50Z Alternation-based lexicon reconstruction Baldwin, Timothy Bond, Francis School of Humanities and Social Sciences International Conference on Theoretical and Methodological Issues in Machine Translation (9th : 2002 : Keihanna, Japan) DRNTU::Humanities::Language::Japanese This research is aimed at developing a hierarchical alternation-based lexical architecture for machine translation. The proposed architecture makes extensive use of information sharing in describing valency frames through derivational links from base frames, rather than as independent entities. This has advantages in descriptive efficiency, robustness and maintainability. The lexicon being developed is built up automatically from the Japanese component of an existing Japanese-English machine translation lexicon. The reconstruction process consists of analysing consistencies in selectional restrictions between valency frames, and postulating alternations where selectional restrictions are preserved on matching case slots; this was found to perform at 60.9% accuracy. All alternation candidates are incorporated into the final-version lexicon as derivational links, and expanded out at run time. Accepted version 2010-09-08T03:18:59Z 2019-12-06T18:18:50Z 2010-09-08T03:18:59Z 2019-12-06T18:18:50Z 2002 2002 Conference Paper Baldwin, T., & Bond, F. (2002). Alternation-based lexicon reconstruction. In proceedings of the 9th International Conference on Theoretical and Methodological Issues in Machine Translation: TMI-2002: (pp.1-11). https://hdl.handle.net/10356/92184 http://hdl.handle.net/10220/6437 155566 en 11 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Humanities::Language::Japanese
spellingShingle DRNTU::Humanities::Language::Japanese
Baldwin, Timothy
Bond, Francis
Alternation-based lexicon reconstruction
description This research is aimed at developing a hierarchical alternation-based lexical architecture for machine translation. The proposed architecture makes extensive use of information sharing in describing valency frames through derivational links from base frames, rather than as independent entities. This has advantages in descriptive efficiency, robustness and maintainability. The lexicon being developed is built up automatically from the Japanese component of an existing Japanese-English machine translation lexicon. The reconstruction process consists of analysing consistencies in selectional restrictions between valency frames, and postulating alternations where selectional restrictions are preserved on matching case slots; this was found to perform at 60.9% accuracy. All alternation candidates are incorporated into the final-version lexicon as derivational links, and expanded out at run time.
author2 School of Humanities and Social Sciences
author_facet School of Humanities and Social Sciences
Baldwin, Timothy
Bond, Francis
format Conference or Workshop Item
author Baldwin, Timothy
Bond, Francis
author_sort Baldwin, Timothy
title Alternation-based lexicon reconstruction
title_short Alternation-based lexicon reconstruction
title_full Alternation-based lexicon reconstruction
title_fullStr Alternation-based lexicon reconstruction
title_full_unstemmed Alternation-based lexicon reconstruction
title_sort alternation-based lexicon reconstruction
publishDate 2010
url https://hdl.handle.net/10356/92184
http://hdl.handle.net/10220/6437
_version_ 1681034121026994176