Forskning ved Københavns Universitet - Københavns Universitet

Forside

Cross-lingual Visual Verb Sense Disambiguation

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Recent work has shown that visual context improves cross-lingual sense disambiguation for nouns. We extend this line of work to the more challenging task of cross-lingual verb sense disambiguation, introducing the MultiSense dataset of 9,504 images annotated with English, German, and Spanish verbs. Each image in MultiSense is annotated with an English verb and its translation in German or Spanish. We show that cross-lingual verb sense disambiguation models benefit from visual context, compared to unimodal baselines. We also show that the verb sense predicted by our best disambiguation model can improve the results of a text-only machine translation system when used for a multimodal translation task.
OriginalsprogEngelsk
TitelProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Antal sider7
ForlagAssociation for Computational Linguistics
Publikationsdato1 jun. 2019
Sider1998-2004
DOI
StatusUdgivet - 1 jun. 2019
Begivenhed2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019 - Minneapolis, USA
Varighed: 3 jun. 20197 jun. 2019

Konference

Konference2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - NAACL-HLT 2019
LandUSA
ByMinneapolis
Periode03/06/201907/06/2019

ID: 230849882