arXiv:1709.03814

SYSTRAN Purely Neural MT Engines for WMT2017

Yongchao Deng, Jungi Kim, Guillaume Klein, Catherine Kobus, Natalia Segal, Christophe Servan, Bo wang, Dakun Zhang, Josep Crego, Jean Senellart

제출 2017-09-12

원문 초록

This paper describes SYSTRAN's systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions. Our systems are built using OpenNMT, an open-source neural machine translation system, implementing sequence-to-sequence models with LSTM encoder/decoders and attention. We experimented using monolingual data automatically back-translated. Our resulting models are further hyper-specialised with an adaptation technique that finely tunes models according to the evaluation test sentences.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.