A shared task on multimodal machine translation and crosslingual image description

Lucia Specia; Stella Frank; Khalil Sima'an; Desmond Elliott

A shared task on multimodal machine translation and crosslingual image description

Lucia Specia, Stella Frank, Khalil Sima'an, Desmond Elliott

Abstract

This paper introduces and summarises the findings of a new shared task at the intersection of Natural Language Processing and Computer Vision: the generation of image descriptions in a target language, given an image and/or one or more descriptions in a different (source) language. This challenge was organised along with the Conference on Machine Translation (WMT16), and called for system submissions for two task variants: (i) a translation task, in which a source language image description needs to be translated to a target language, (optionally) with additional cues from the corresponding image, and (ii) a description generation task, in which a target language description needs to be generated for an image, (optionally) with additional cues from source language descriptions of the same image. In this first edition of the shared task, 16 systems were submitted for the translation task and seven for the image description task, from a total of 10 teams.

Original language	Undefined/Unknown
Title of host publication	Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers
Number of pages	11
Volume	2
Publication date	2016
Pages	543-553
Publication status	Published - 2016

Cite this

A shared task on multimodal machine translation and crosslingual image description. / Specia, Lucia; Frank, Stella; Sima'an, Khalil et al.

Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers. Vol. 2 2016. p. 543-553.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

@inproceedings{cb78550973a84f87a377f70cff04d1e4,

title = "A shared task on multimodal machine translation and crosslingual image description",

abstract = "This paper introduces and summarises the findings of a new shared task at the intersection of Natural Language Processing and Computer Vision: the generation of image descriptions in a target language, given an image and/or one or more descriptions in a different (source) language. This challenge was organised along with the Conference on Machine Translation (WMT16), and called for system submissions for two task variants: (i) a translation task, in which a source language image description needs to be translated to a target language, (optionally) with additional cues from the corresponding image, and (ii) a description generation task, in which a target language description needs to be generated for an image, (optionally) with additional cues from source language descriptions of the same image. In this first edition of the shared task, 16 systems were submitted for the translation task and seven for the image description task, from a total of 10 teams.",

author = "Lucia Specia and Stella Frank and Khalil Sima'an and Desmond Elliott",

year = "2016",

language = "Udefineret/Ukendt",

volume = "2",

pages = "543--553",

booktitle = "Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers",

}

TY - GEN

T1 - A shared task on multimodal machine translation and crosslingual image description

AU - Specia, Lucia

AU - Frank, Stella

AU - Sima'an, Khalil

AU - Elliott, Desmond

PY - 2016

Y1 - 2016

N2 - This paper introduces and summarises the findings of a new shared task at the intersection of Natural Language Processing and Computer Vision: the generation of image descriptions in a target language, given an image and/or one or more descriptions in a different (source) language. This challenge was organised along with the Conference on Machine Translation (WMT16), and called for system submissions for two task variants: (i) a translation task, in which a source language image description needs to be translated to a target language, (optionally) with additional cues from the corresponding image, and (ii) a description generation task, in which a target language description needs to be generated for an image, (optionally) with additional cues from source language descriptions of the same image. In this first edition of the shared task, 16 systems were submitted for the translation task and seven for the image description task, from a total of 10 teams.

AB - This paper introduces and summarises the findings of a new shared task at the intersection of Natural Language Processing and Computer Vision: the generation of image descriptions in a target language, given an image and/or one or more descriptions in a different (source) language. This challenge was organised along with the Conference on Machine Translation (WMT16), and called for system submissions for two task variants: (i) a translation task, in which a source language image description needs to be translated to a target language, (optionally) with additional cues from the corresponding image, and (ii) a description generation task, in which a target language description needs to be generated for an image, (optionally) with additional cues from source language descriptions of the same image. In this first edition of the shared task, 16 systems were submitted for the translation task and seven for the image description task, from a total of 10 teams.

M3 - Konferencebidrag i proceedings

VL - 2

SP - 543

EP - 553

BT - Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

ER -