Papers › Towards Neural Phrase-based Machine Translation

Towards Neural Phrase-based Machine Translation

17 Jun 2017ICLR 2018 1arXiv:1706.05565archive 2025-07-28

Po-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

posenhuang/NPMT officialmentioned in papermentioned on GitHubtorch report
Microsoft/NPMT mentioned on GitHubtorch report
ykrmm/ICLR_2020 mentioned on GitHubpytorch report
ykrmm/TREMBA mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Machine TranslationNMTTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation IWSLT2014 German-English Neural PBMT + LM [Huang2018] BLEU score 30.08 #32 of 34 Archive leaderboard report
Machine Translation IWSLT2015 English-German NPMT + language model BLEU score 25.36 #7 of 8 Archive leaderboard report
Machine Translation IWSLT2015 German-English NPMT + language model BLEU score 30.08 #8 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections