Forskning ved Københavns Universitet - Københavns Universitet

Forside

Adversarial Evaluation of Multimodal Machine Translation

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

The promise of combining vision and language in multimodal machine translation is that systems will produce better translations by leveraging the image data. However, inconsistent results have lead to uncertainty about whether the images actually improve translation quality. We present an adversarial evaluation method to directly examine the utility of the image data in this task. Our evaluation measures whether multimodal translation systems perform better given either the congruentimage or a random incongruent image, in add ition to the correct source language sentence. We find that two out of three publicly available systems are sensitive to this perturbation of the data, and recommend that all systems pass this evaluation in the future
OriginalsprogEngelsk
TitelProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Antal sider5
ForlagAssociation for Computational Linguistics
Publikationsdato2018
Sider2974-2978
ISBN (Trykt)978-1-948087-84-1
StatusUdgivet - 2018
Begivenhed2018 Conference on Empirical Methods in Natural Language Processing - Brussels, Belgien
Varighed: 31 okt. 20184 nov. 2018

Konference

Konference2018 Conference on Empirical Methods in Natural Language Processing
LandBelgien
ByBrussels
Periode31/10/201804/11/2018

Links

ID: 230797240