Conceptual transfer: Using local classifiers for transfer selection

Gregor Thurmair


Abstract
A key challenge for Machine Translation is transfer selection, i.e. to find the right translation for a given word from a set of alternatives (1:n). This problem becomes the more important the larger the dictionary is, as the number of alternatives increases. The contribution presents a novel approach for transfer selection, called conceptual transfer, where selection is done using classifiers based on the conceptual context of a translation candidate on the source language side. Such classifiers are built automatically by parallel corpus analysis: Creating subcorpora for each translation of a 1:n package, and identifying correlating concepts in these subcorpora as features of the classifier. The resulting resource can easily be linked to transfer components of MT systems as it does not depend on internal analysis structures. Tests show that conceptual transfer outperforms the selection techniques currently used in operational MT systems.
Anthology ID:
L14-1523
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
4387–4393
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/661_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Gregor Thurmair. 2014. Conceptual transfer: Using local classifiers for transfer selection. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4387–4393, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
Conceptual transfer: Using local classifiers for transfer selection (Thurmair, LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/661_Paper.pdf