Neural Machine Translation with Joint Representation

02/16/2020 ∙ by Yanyang Li, et al. ∙ 0

Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Machine Translation (NMT) systems resort to the attention which partially encodes the interaction for efficiency. In this paper, we employ Joint Representation that fully accounts for each possible interaction. We sidestep the inefficiency issue by refining representations with the proposed efficient attention operation. The resulting Reformer models offer a new Sequence-to- Sequence modelling paradigm besides the Encoder-Decoder framework and outperform the Transformer baseline in either the small scale IWSLT14 German-English, English-German and IWSLT15 Vietnamese-English or the large scale NIST12 Chinese-English translation tasks by about 1 BLEU point.We also propose a systematic model scaling approach, allowing the Reformer model to beat the state-of-the-art Transformer in IWSLT14 German-English and NIST12 Chinese-English with about 50 code is publicly available at https://github.com/lyy1994/reformer.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

Code Repositories

reformer

An NMT framework built on top of Joint Representation


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.