A reinforcement learning approach to interactive-predictive neural machine translation

• Autores: Tsz Kin Lam, Julia Kreutzer, Stefan Riezler
• Localización: Proceedings of the 21st Annual Conference of the European Association for Machine Translation: 28-30 May 2018, Universitat d'Alacant, Alacant, Spain / coord. por Juan Antonio Pérez Ortiz, Felipe Sánchez Martínez, Miquel Esplà Gomis, Maja Popovic, Celia Rico Pérez, André Martins, Joachim Van den Bogaert, Mikel L. Forcada Zubizarreta, 2018, ISBN 978-84-09-01901-4, págs. 169-178
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • We present an approach to interactive-predictive 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.