Papers › Distilling Translations with Visual Awareness

Distilling Translations with Visual Awareness

18 Jun 2019ACL 2019 7arXiv:1906.07701archive 2025-07-28

Julia Ive, Pranava Madhyastha, Lucia Specia

Previous work on multimodal machine translation has shown that visual information is only needed in very specific cases, for example in the presence of ambiguous words where the textual context is not sufficient. As a consequence, models tend to learn to ignore this information. We propose a translate-and-refine approach to this problem where images are only used by a second stage decoder. This approach is trained jointly to generate a good first draft translation and to improve over this draft by (i) making better use of the target language textual context (both left and right-side contexts) and (ii) making use of visual context. This approach leads to the state of the art results. Additionally, we show that it has the ability to recover from erroneous or missing words in the source language.

PaperPDFConference PDFCode

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

Code

ImperialNLP/MMT-Delib officialmentioned in papertf 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

DecoderMachine TranslationMultimodal Machine TranslationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multimodal Machine Translation Multi30K del+obj BLEU (EN-DE) 38 #8 of 15 Archive leaderboard report
Multimodal Machine Translation Multi30K del+obj Meteor (EN-DE) 55.6 #8 of 15 Archive leaderboard report
Multimodal Machine Translation Multi30K del Meteor (EN-FR) 74.6 #15 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