Paper: Refinements to Interactive Translation Prediction Based on Search Graphs

ACL ID P14-2094
Title Refinements to Interactive Translation Prediction Based on Search Graphs
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We propose a number of refinements to the canonical approach to interactive trans- lation prediction. By more permissive matching criteria, placing emphasis on matching the last word of the user prefix, and dealing with predictions to partially typed words, we observe gains in both word prediction accuracy (+5.4%) and let- ter prediction accuracy (+9.3%).