19 December 2017 Modeling and prediction of human word search behavior in interactive machine translation
Author Affiliations +
Proceedings Volume 10613, 2017 International Conference on Robotics and Machine Vision; 106130H (2017) https://doi.org/10.1117/12.2300343
Event: Second International Conference on Robotics and Machine Vision, 2017, Kitakyushu, Japan
Abstract
As a kind of computer aided translation method, Interactive Machine Translation technology reduced manual translation repetitive and mechanical operation through a variety of methods, so as to get the translation efficiency, and played an important role in the practical application of the translation work. In this paper, we regarded the behavior of users' frequently searching for words in the translation process as the research object, and transformed the behavior to the translation selection problem under the current translation. The paper presented a prediction model, which is a comprehensive utilization of alignment model, translation model and language model of the searching words behavior. It achieved a highly accurate prediction of searching words behavior, and reduced the switching of mouse and keyboard operations in the users' translation process.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Duo Ji, Bai Yu, Bin Ma, Na Ye, "Modeling and prediction of human word search behavior in interactive machine translation", Proc. SPIE 10613, 2017 International Conference on Robotics and Machine Vision, 106130H (19 December 2017); doi: 10.1117/12.2300343; https://doi.org/10.1117/12.2300343
PROCEEDINGS
6 PAGES


SHARE
Back to Top