LeBLEU: N-gram-based Translation Evaluation Score for Morphologically Complex Languages
2015pp. 411–416
Citations Over TimeTop 10% of 2015 papers
Abstract
This paper describes the LeBLEU evaluation score for machine translation, submitted to WMT15 Metrics Shared Task. LeBLEU extends the popular BLEU score to consider fuzzy matches between word n-grams. While there are several variants of BLEU that allow to non-exact matches between words either by character-based distance measures or morphological preprocessing, none of them use fuzzy comparison between longer chunks of text. The results on WMT data sets show that fuzzy n-gram matching improves correlations to human evaluation especially for highly compounding languages.
Related Papers
- → Neural Machine Translation of Indian Languages(2017)44 cited
- Better Evaluation Metrics Lead to Better Machine Translation(2011)
- Statistical Machine Translation with Rule based Machine Translation.(2011)
- → On Using Monolingual Corpora in Neural Machine Translation(2015)512 cited
- → Factored Statistical Machine Translation for German-English(2018)