Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Towards Neural Phrase-based Machine Translation
Po-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng
Feb 15, 2018 (modified: Feb 24, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new layer to perform (soft) local reordering of input sequences. Different from existing neural machine translation (NMT) approaches, NPMT does not use attention-based decoding mechanisms. Instead, it directly outputs phrases in a sequential order and can decode in linear time. Our experiments show that NPMT achieves superior performances on IWSLT 2014 German-English/English-German and IWSLT 2015 English-Vietnamese machine translation tasks compared with strong NMT baselines. We also observe that our method produces meaningful phrases in output languages.
TL;DR:Neural phrase-based machine translation with linear decoding time
Keywords:Neural Machine Translation, Sequence to Sequence, Sequence Modeling
Enter your feedback below and we'll get back to you as soon as possible.