papers AI Learner
The Github is limit! Click to go to the new site.

Learning from Chunk-based Feedback in Neural Machine Translation

2018-06-19
Pavel Petrushkov, Shahram Khadivi, Evgeny Matusov

Abstract

We empirically investigate learning from partial feedback in neural machine translation (NMT), when partial feedback is collected by asking users to highlight a correct chunk of a translation. We propose a simple and effective way of utilizing such feedback in NMT training. We demonstrate how the common machine translation problem of domain mismatch between training and deployment can be reduced solely based on chunk-level user feedback. We conduct a series of simulation experiments to test the effectiveness of the proposed method. Our results show that chunk-level feedback outperforms sentence based feedback by up to 2.61% BLEU absolute.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1806.07169

PDF

https://arxiv.org/pdf/1806.07169


Comments

Content