BEER: BEtter Evaluation as Ranking

Milos Stanojevic, Khalil Sima'an

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We present the UvA-ILLC submission of the BEER metric to WMT 14 metrics task. BEER is a sentence level metric that can incorporate a large number of features combined in a linear model. Novel contributions are (1) efficient tuning of a large number of features for maximizing correlation with human system ranking, and (2) novel features that give smoother sentence level scores.
Original languageEnglish
Title of host publicationProceedings of the Ninth Workshop on Statistical Machine Translation
Place of PublicationBaltimore, Maryland, USA
PublisherAssociation for Computational Linguistics (ACL)
Pages414-419
Number of pages6
DOIs
Publication statusPublished - Jun 2014
EventNinth Workshop on Statistical Machine Translation - Baltimore, United States
Duration: 26 Jun 201427 Jun 2014
http://www.statmt.org/wmt14/

Conference

ConferenceNinth Workshop on Statistical Machine Translation
Country/TerritoryUnited States
CityBaltimore
Period26/06/1427/06/14
Internet address

Fingerprint

Dive into the research topics of 'BEER: BEtter Evaluation as Ranking'. Together they form a unique fingerprint.

Cite this