Abstract

In this paper we describe two new objective automatic evaluation methods for machine translation. The first method is based on longest common subsequence between a candidate translation and a set of reference translations. Longest common subsequence takes into account sentence level structure similarity naturally and identifies longest co-occurring insequence n-grams automatically. The second method relaxes strict n-gram matching to skipbigram matching. Skip-bigram is any pair of words in their sentence order. Skip-bigram cooccurrence statistics measure the overlap of skip-bigrams between a candidate translation and a set of reference translations. The empirical results show that both methods correlate with human judgments very well in both adequacy and fluency. 1

Keywords

BigramComputer scienceMachine translationLongest common subsequence problemArtificial intelligenceSet (abstract data type)Natural language processingSubsequenceEvaluation of machine translationTranslation (biology)Matching (statistics)Similarity (geometry)Speech recognitionPattern matchingPattern recognition (psychology)AlgorithmTrigramStatisticsMathematicsExample-based machine translation

Affiliated Institutions

Related Publications

Publication Info

Year
2004
Type
article
Pages
605-es
Citations
708
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

708
OpenAlex

Cite This

Chin-Yew Lin, Franz Josef Och (2004). Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. , 605-es. https://doi.org/10.3115/1218955.1219032

Identifiers

DOI
10.3115/1218955.1219032