Paper: Evaluating Machine Translations Using mNCD

ACL ID P10-2015
Title Evaluating Machine Translations Using mNCD
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2010
Authors

This paper introduces mNCD, a method for automatic evaluation of machine trans- lations. The measure is based on nor- malized compression distance (NCD), a general information theoretic measure of string similarity, and flexible word match- ing provided by stemming and synonyms. The mNCD measure outperforms NCD in system-level correlation to human judg- ments in English.