Toward a science of machine translation

DSpace/Manakin Repository


Search DR-NTU

Advanced Search Subject Search


My Account

Toward a science of machine translation

Show simple item record

dc.contributor.author Bond, Francis.
dc.date.accessioned 2011-10-17T01:12:44Z
dc.date.available 2011-10-17T01:12:44Z
dc.date.copyright 2002
dc.date.issued 2011-10-17
dc.identifier.citation Bond, F. (2002). Toward a science of machine translation. Proceedings of the MT Roadmap Workshop at TMI-2002.
dc.identifier.uri http://hdl.handle.net/10220/7273
dc.description.abstract The fact that machine translation output does not reach the level of good human translations is well known. However, there has been surprisingly little attention paid by the machine translation community to how humans achieve such results. In this paper, I suggest several ways to improve machine translation, based on the best practices of human translators, as described in Nida's (1964) Toward a Science of Translating. I call this approach multi-pass machine translation (MPMT), as it crucially relies on processing the text more than once. It is similar to the opportunistic bricoleur approach of Gdaniec (1999) in that it sets out to use the means at hand, adding to or changing them as necessary. As Sch utz (2001) points out, much of the research in the past decade has concentrated on the important but non-core issues of integrating MT into DTP formats and HTML. In this paper I concentrate on improving the MT engine itself. The resulting approach integrates much recent research into a single system.
dc.format.extent 8 p.
dc.language.iso en
dc.rights © 2002 Proceedings of the MT Roadmap Workshop at TMI.
dc.subject DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
dc.title Toward a science of machine translation
dc.type Conference Paper
dc.contributor.conference International Conference on Theoretical and Methodological Issues in Machine Translation (9th : 2002 : Keihanna, Japan)
dc.contributor.school School of Humanities and Social Sciences
dc.description.version Accepted version
dc.identifier.rims 155564

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record


Total views

All Items Views
Toward a science of machine translation 562

Total downloads

All Bitstreams Views
2002-roadmap-mpmt.pdf 5

Top country downloads

Country Code Views
Singapore 4

Top city downloads

city Views
Singapore 4