Paper: A Rule-Augmented Statistical Phrase-based Translation System

ACL ID P14-5013
Title A Rule-Augmented Statistical Phrase-based Translation System
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014

Interactive or Incremental Statistical Ma- chine Translation (IMT) aims to provide a mechanism that allows the statistical mod- els involved in the translation process to be incrementally updated and improved. The source of knowledge normally comes from users who either post-edit the entire trans- lation or just provide the translations for wrongly translated domain-specific termi- nologies. Most of the existing work on IMT uses batch learning paradigm which does not allow translation systems to make use of the new input instantaneously. We introduce an adaptive MT framework with a Rule Definition Language (RDL) for users to amend MT results through trans- lation rules or patterns. Experimental re- sults show that our system acknowledges user feedback via RDL which improves the translation...