paper-with-me

홈 › Papers

Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation

2019-07-04 · WS 2019 8 · Tsz Kin Lam, Shigehiko Schamoni, Stefan Riezler

We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain locations identified by the system. Responses are weak feedback in the form of "keep" and "delete" edits, and expert demonstrations in the form of "substitute" edits. Conditioning on the collected feedback, the system creates alternative translations via constrained beam search. In simulation experiments on two language pairs our systems get close to the performance of supervised training with much less human effort.

📄 PDF Abstract BibTeX arXiv:1907.02326

Code (0)

등록된 구현이 없습니다.

Tasks

FormImitation LearningMachine TranslationTranslation

Similar Papers 제목 키워드 기반

A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation

2018-05-03 · Tsz Kin Lam, Julia Kreutzer, Stefan Riezler

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 empl…

Machine Translationreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Introducing Mouse Actions into Interactive-Predictive Neural Machine Translation

2021-08-01 · MTSummit 2021 8 · Ángel Navarro, Francisco Casacuberta

The quality of the translations generated by Machine Translation (MT) systems has highly improved through the years and but we are still far away to obtain fully automatic high-quality translations. To generate them and …

Machine TranslationTranslation

Interactive-Predictive Machine Translation based on Syntactic Constraints of Prefix

2016-12-01 · COLING 2016 12 · Na Ye, Guiping Zhang, Dongfeng Cai

Interactive-predictive machine translation (IPMT) is a translation mode which combines machine translation technology and human behaviours. In the IPMT system, the utilization of the prefix greatly affects the interactio…

Machine TranslationQuestion AnsweringTranslation

Investigating Active Learning in Interactive Neural Machine Translation

2021-08-01 · MTSummit 2021 8 · Kamal Gupta, Dhanvanth Boppana, Rejwanul Haque, Asif Ekbal 외

Interactive-predictive translation is a collaborative iterative process and where human translators produce translations with the help of machine translation (MT) systems interactively. Various sampling techniques in act…

Active LearningMachine TranslationNMTSentence+2

Modelling Source- and Target- Language Syntactic Information as Conditional Context in Interactive Neural Machine Translation

2020-11-01 · EAMT 2020 11 · Kamal Kumar Gupta, Rejwanul Haque, Asif Ekbal, Pushpak Bhattacharyya 외

In interactive machine translation (MT), human translators correct errors in automatic translations in collaboration with the MT systems, which is seen as an effective way to improve the productivity gain in translation.…

Machine TranslationNMTTranslation