Papers › Learning Joint Multilingual Sentence Representations with Neural Machine Translation

Learning Joint Multilingual Sentence Representations with Neural Machine Translation

13 Apr 2017WS 2017 8arXiv:1704.04154archive 2025-07-28

Holger Schwenk, Matthijs Douze

In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages. Our aim is that a representation which is independent of the language, is likely to capture the underlying semantics. We define a new cross-lingual similarity measure, compare up to 1.4M sentence representations and study the characteristics of close sentences. We provide experimental evidence that sentences that are close in embedding space are indeed semantically highly related, but often have quite different structure and syntax. These relations also hold when comparing sentences in different 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

Unbabel/COMET 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

Joint Multilingual Sentence RepresentationsMachine TranslationSentenceTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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