UZH-Logo

Maintenance Infos

TerrorCat: a translation error categorization-based MT quality metric


Fishel, Mark; Sennrich, Rico; Popović, Maja; Bojar, Ondřej (2012). TerrorCat: a translation error categorization-based MT quality metric. In: NAACL 2012 7th workshop on Statistical Machine Translation, Montreal, Canada, 7 June 2012 - 8 June 2012, 64-70.

Abstract

We present TerrorCat, a submission to the WMT’12 metrics shared task. TerrorCat uses frequencies of automatically obtained translation error categories as base for pairwise comparison of translation hypotheses, which is in turn used to generate a score for every translation. The metric shows high overall correlation with human judgements on the system level and more modest results on the level of individual sentences.

We present TerrorCat, a submission to the WMT’12 metrics shared task. TerrorCat uses frequencies of automatically obtained translation error categories as base for pairwise comparison of translation hypotheses, which is in turn used to generate a score for every translation. The metric shows high overall correlation with human judgements on the system level and more modest results on the level of individual sentences.

Citations

Altmetrics

Downloads

105 downloads since deposited on 13 Jul 2012
34 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:8 June 2012
Deposited On:13 Jul 2012 07:14
Last Modified:05 Apr 2016 15:52
Publisher:Association for Computational Linguistics
ISBN:978-1-937284-20-6
Official URL:http://www.aclweb.org/anthology-new/W/W12/W12-3105.pdf
Permanent URL: https://doi.org/10.5167/uzh-63325

Download

[img]
Preview
Content: Published Version
Filetype: PDF
Size: 128kB

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations