A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation

Tsz Kin Lam, Julia Kreutzer, Stefan Riezler


Abstract
We present an approach to interactivepredictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations. Secondly, human effort is further reduced by using the entropy of word predictions as uncertainty criterion to trigger feedback requests. Lastly, online updates of the model parameters after every interaction allow the model to adapt quickly. We show in simulation experiments that reward signals on partial translations significantly improve character F-score and BLEU compared to feedback on full translations only, while human effort can be reduced to an average number of 5 feedback requests for every input.
Anthology ID:
2018.eamt-main.17
Volume:
Proceedings of the 21st Annual Conference of the European Association for Machine Translation
Month:
May
Year:
2018
Address:
Alicante, Spain
Editors:
Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Maja Popović, Celia Rico, André Martins, Joachim Van den Bogaert, Mikel L. Forcada
Venue:
EAMT
SIG:
Publisher:
Note:
Pages:
189–198
Language:
URL:
https://aclanthology.org/2018.eamt-main.17
DOI:
Bibkey:
Cite (ACL):
Tsz Kin Lam, Julia Kreutzer, and Stefan Riezler. 2018. A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation, pages 189–198, Alicante, Spain.
Cite (Informal):
A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation (Lam et al., EAMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.eamt-main.17.pdf