IPA and STOUT: leveraging linguistic and source-based features for machine translation evaluation
Document typeConference lecture
PublisherAssociation for Computational Linguistics
Rights accessRestricted access - publisher's policy
This paper describes the UPC submissions to the WMT14 Metrics Shared Task : UPC-IPA and UPC-STOUT. These metrics use a collection of evaluation measures integrated in ASIYA, a toolkit for machine translation evaluation. In addition to some standard metrics, the two submissions take advantage of novel metrics that consider linguistic structures, lexical relationships, and semantics to compare both source and reference translation against the candidate translation. The new metrics are available for several target languages other than English. In the the official WMT14 evaluation, UPC-IPA and UPC-STOUT scored above the average in 7 out of 9 language pairs at the system level and 8 out of 9 at the segment level.
CitationGonzalez, M.; Barron-Cedeño, A.; Marquez, L. IPA and STOUT: leveraging linguistic and source-based features for machine translation evaluation. A: Workshop on Statistical Machine Translation. "Proceedings of the Ninth Workshop on Statistical Machine Translation". Baltimore: Association for Computational Linguistics, 2014, p. 394-401.
|W14-3351.pdf||article complert||145,8Kb||Restricted access|