Fitting Sentence Level Translation Evaluation with Many Dense Features

Milos Stanojevic, Khalil Sima'an

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

Abstract

Sentence level evaluation in MT has turned out far more difficult than corpus level evaluation. Existing sentence level metrics employ a limited set of features, most of which are rather sparse at the sentence level, and their intricate models are rarely trained for ranking. This paper presents a simple linear model exploiting 33 relatively dense features, some of which are novel while others are known but seldom used, and train it under the learning-to-rank framework. We evaluate our metric on the standard WMT12 data showing that it outperforms the strong baseline METEOR. We also analyze the contribution of individual features and the choice of training data, language-pair vs. target-language data, providing new insights into this task.
Original languageEnglish
Title of host publicationProceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Place of PublicationDoha, Qatar
PublisherAssociation for Computational Linguistics (ACL)
Pages202-206
Number of pages5
DOIs
Publication statusPublished - Oct 2014
Event2014 Conference on Empirical Methods in Natural Language Processing - Doha, Qatar
Duration: 25 Oct 201429 Oct 2014
http://emnlp2014.org/

Conference

Conference2014 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2014
CountryQatar
CityDoha
Period25/10/1429/10/14
Internet address

Cite this