Paper: Towards A Unified Approach To Memory- And Statistical-Based Machine Translation

ACL ID P01-1050
Title Towards A Unified Approach To Memory- And Statistical-Based Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2001
Authors
  • Daniel Marcu (University of Southern California, Marina del Rey CA)

We present a set of algorithms that en- able us to translate natural language sentences by exploiting both a trans- lation memory and a statistical-based translation model. Our results show that an automatically derived transla- tion memory can be used within a sta- tistical framework to often find trans- lations of higher probability than those found using solely a statistical model. The translations produced using both the translation memory and the sta- tistical model are significantly better than translations produced by two com- mercial systems: our hybrid system translated perfectly 58% of the 505 sentences in a test collection, while the commercial systems translated per- fectly only 40-42% of them.