Skip to main navigation Skip to search Skip to main content

The Parameter-optimized ATEC Metric for MT Evaluation

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

This paper describes the latest version of the ATEC metric for automatic MT evaluation, with parameters optimized for word choice and word order, the two fundamental features of language that the metric relies on. The former is assessed by matching at various linguistic levels and weighting the informativeness of both matched and unmatched words. The latter is quantified in term of word position and information flow. We also discuss those aspects of language not yet covered by other existing evaluation metrics but carefully considered in the formulation of our metric. © 2010 Association for Computational Linguistics.
Original languageEnglish
Title of host publicationACL 2010 - Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, Proceedings of the Workshop
EditorsChris Callison-Burch, Philipp Koehn, Christof Monz, Kay Peterson, Omar Zaidan
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics
Pages360-364
ISBN (Print)9781932432718, 193243271X
Publication statusPublished - Jul 2010
EventJoint 5th Workshop on Statistical Machine Translation and MetricsMATR (WMT10) - Uppsala, Sweden
Duration: 15 Jul 201016 Jul 2010
https://machinetranslate.org/wmt10

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

ConferenceJoint 5th Workshop on Statistical Machine Translation and MetricsMATR (WMT10)
Abbreviated titleWMT’10/MetricsMATR
PlaceSweden
CityUppsala
Period15/07/1016/07/10
Internet address

Fingerprint

Dive into the research topics of 'The Parameter-optimized ATEC Metric for MT Evaluation'. Together they form a unique fingerprint.

Cite this