TY - GEN
T1 - Hunter NMT System for WMT18 Biomedical Translation Task
T2 - 3rd Conference on Machine Translation, WMT 2018 at the Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
AU - Khan, Abdul Rafae
AU - Panda, Subhadarshi
AU - Xu, Jia
AU - Flokas, Lampros
N1 - Publisher Copyright:
©2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - This paper describes the submission of Hunter Neural Machine Translation (NMT) to the WMT’18 Biomedical translation task from English to French. The discrepancy between training and test data distribution brings a challenge to translate text in new domains. Beyond the previous work of combining in-domain with out-of-domain models, we found accuracy and efficiency gain in combining different in-domain models. We conduct extensive experiments on NMT with transfer learning. We train on different in-domain Biomedical datasets one after another. That means parameters of the previous training serve as the initialization of the next one. Together with a pre-trained out-of-domain News model, we enhanced translation quality with 3.73 BLEU points over the baseline. Furthermore, we applied ensemble learning on training models of intermediate epochs and achieved an improvement of 4.02 BLEU points over the baseline. Overall, our system is 11.29 BLEU points above the best system of last year on the EDP 2017 test set.
AB - This paper describes the submission of Hunter Neural Machine Translation (NMT) to the WMT’18 Biomedical translation task from English to French. The discrepancy between training and test data distribution brings a challenge to translate text in new domains. Beyond the previous work of combining in-domain with out-of-domain models, we found accuracy and efficiency gain in combining different in-domain models. We conduct extensive experiments on NMT with transfer learning. We train on different in-domain Biomedical datasets one after another. That means parameters of the previous training serve as the initialization of the next one. Together with a pre-trained out-of-domain News model, we enhanced translation quality with 3.73 BLEU points over the baseline. Furthermore, we applied ensemble learning on training models of intermediate epochs and achieved an improvement of 4.02 BLEU points over the baseline. Overall, our system is 11.29 BLEU points above the best system of last year on the EDP 2017 test set.
UR - http://www.scopus.com/inward/record.url?scp=85089684378&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089684378&partnerID=8YFLogxK
U2 - 10.18653/v1/W18-64074
DO - 10.18653/v1/W18-64074
M3 - Conference contribution
AN - SCOPUS:85089684378
T3 - WMT 2018 - 3rd Conference on Machine Translation, Proceedings of the Conference
SP - 655
EP - 661
BT - Shared Task Papers
Y2 - 31 October 2018 through 1 November 2018
ER -