Interactive-Predictive Translation Based on Multiple Word-Segments

Current machine translation systems require human revision to produce high-quality translations. This is achieved through a post-editing process or by means of an interactive human–computer collaboration. Most protocols belonging to the last scenario follow a left-to-right strategy, where the prefix of the translation is iteratively increased by successive validations and corrections made by the user. In this work, we propose a new interactive protocol which allows the user to validate all correct word sequences in the translation generated by the system, breaking the left-to-right barrier. We evaluated our proposal through simulated experiments, obtaining large reductions of the human effort.