@inproceedings{gella-etal-2019-cross,
title = "Cross-lingual Visual Verb Sense Disambiguation",
author = "Gella, Spandana and
Elliott, Desmond and
Keller, Frank",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1200",
doi = "10.18653/v1/N19-1200",
pages = "1998--2004",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gella-etal-2019-cross">
<titleInfo>
<title>Cross-lingual Visual Verb Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Keller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">gella-etal-2019-cross</identifier>
<identifier type="doi">10.18653/v1/N19-1200</identifier>
<location>
<url>https://aclanthology.org/N19-1200</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1998</start>
<end>2004</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Visual Verb Sense Disambiguation
%A Gella, Spandana
%A Elliott, Desmond
%A Keller, Frank
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F gella-etal-2019-cross
%X 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.
%R 10.18653/v1/N19-1200
%U https://aclanthology.org/N19-1200
%U https://doi.org/10.18653/v1/N19-1200
%P 1998-2004
Markdown (Informal)
[Cross-lingual Visual Verb Sense Disambiguation](https://aclanthology.org/N19-1200) (Gella et al., NAACL 2019)
ACL
- Spandana Gella, Desmond Elliott, and Frank Keller. 2019. Cross-lingual Visual Verb Sense Disambiguation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1998–2004, Minneapolis, Minnesota. Association for Computational Linguistics.