Unsupervised measurement of translation quality using multi-engine, bi-directional translation

Menno van Zaanen, Simon Zwarts

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Lay people discussing machine translation systems often perform a round trip translation, that is translating a text into a foreign language and back, to measure the quality of the system. The idea behind this is that a good system will produce a round trip translation that is exactly (or perhaps very close to) the original text. However, people working with machine translation systems intuitively know that round trip translation is not a good evaluation method. In this article we will show empirically that round trip translation cannot be used as a measure of the quality of a machine translation system. Even when using translations of multiple machine translation systems into account, to reduce the impact of errors of a single system, round trip translation cannot be used to measure machine translation quality.
Original languageEnglish
Title of host publicationAI 2006
Subtitle of host publicationadvances in artificial intelligence : 19th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, December 4-8, 2006 : proceedings
EditorsAbdul Sattar, Byeong Ho Kang
Place of PublicationBerlin
PublisherSpringer, Springer Nature
Pages1208-1214
Number of pages7
ISBN (Print)3540497870
DOIs
Publication statusPublished - 2006
EventAustralian Joint Conference on Artificial Intelligence (19th : 2006) - Hobart
Duration: 4 Dec 20068 Dec 2006

Publication series

NameLecture notes in computer science
PublisherSpringer-Verlag
Volume4304

Conference

ConferenceAustralian Joint Conference on Artificial Intelligence (19th : 2006)
CityHobart
Period4/12/068/12/06

Fingerprint

Dive into the research topics of 'Unsupervised measurement of translation quality using multi-engine, bi-directional translation'. Together they form a unique fingerprint.

Cite this