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.
@article{arxiv.1806.07169,
title = {Learning from Chunk-based Feedback in Neural Machine Translation},
author = {Pavel Petrushkov and Shahram Khadivi and Evgeny Matusov},
journal= {arXiv preprint arXiv:1806.07169},
year = {2018}
}
Comments
the paper accepted in ACL 2018 Conference, Melbourne, Australia