Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description

Desmond Elliott; Stella Frank; Loïc Barrault; Fethi Bougares; Lucia Specia

Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description

Desmond Elliott, Stella Frank, Loïc Barrault, Fethi Bougares, Lucia Specia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present the results from the second shared task on multimodal machine translation and multilingual image description. Nine teams submitted 19 systems to two tasks. The multimodal translation task, in which the source sentence is supplemented by an image, was extended with a new language (French) and two new test sets. The multilingual image description task was changed such that at test time, only the image is given. Compared to last year, multimodal systems improved, but text-only systems remain competitive.

Original language	English
Title of host publication	Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers
Place of Publication	Copenhagen, Denmark
Publisher	Association for Computational Linguistics
Pages	215-233
Number of pages	19
Publication status	Published - 1 Sept 2017
Event	Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description 2017 - Copenhagen, Denmark Duration: 7 Sept 2017 → 8 Sept 2017 http://www.statmt.org/wmt17/index.html

Conference

Conference	Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description 2017
Abbreviated title	WMT17
Country/Territory	Denmark
City	Copenhagen
Period	7/09/17 → 8/09/17
Internet address	http://www.statmt.org/wmt17/index.html

Access to Document

WMT18Final published version, 1.98 MBLicence: Creative Commons: Attribution (CC-BY)

http://www.aclweb.org/anthology/W17-4718Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{d45428b032db404a8e3f945d91024c54,

title = "Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description",

abstract = "We present the results from the second shared task on multimodal machine translation and multilingual image description. Nine teams submitted 19 systems to two tasks. The multimodal translation task, in which the source sentence is supplemented by an image, was extended with a new language (French) and two new test sets. The multilingual image description task was changed such that at test time, only the image is given. Compared to last year, multimodal systems improved, but text-only systems remain competitive. ",

author = "Desmond Elliott and Stella Frank and Lo{\"i}c Barrault and Fethi Bougares and Lucia Specia",

year = "2017",

month = sep,

day = "1",

language = "English",

pages = "215--233",

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

publisher = "Association for Computational Linguistics",

note = "Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description 2017, WMT17 ; Conference date: 07-09-2017 Through 08-09-2017",

url = "http://www.statmt.org/wmt17/index.html",

}

Elliott, D, Frank, S, Barrault, L, Bougares, F & Specia, L 2017, Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description. in Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers. Association for Computational Linguistics, Copenhagen, Denmark, pp. 215-233, Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description 2017, Copenhagen, Denmark, 7/09/17. <http://www.aclweb.org/anthology/W17-4718>

Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description. / Elliott, Desmond; Frank, Stella; Barrault, Loïc et al.
Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers. Copenhagen, Denmark: Association for Computational Linguistics, 2017. p. 215-233.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description

AU - Elliott, Desmond

AU - Frank, Stella

AU - Barrault, Loïc

AU - Bougares, Fethi

AU - Specia, Lucia

PY - 2017/9/1

Y1 - 2017/9/1

N2 - We present the results from the second shared task on multimodal machine translation and multilingual image description. Nine teams submitted 19 systems to two tasks. The multimodal translation task, in which the source sentence is supplemented by an image, was extended with a new language (French) and two new test sets. The multilingual image description task was changed such that at test time, only the image is given. Compared to last year, multimodal systems improved, but text-only systems remain competitive.

AB - We present the results from the second shared task on multimodal machine translation and multilingual image description. Nine teams submitted 19 systems to two tasks. The multimodal translation task, in which the source sentence is supplemented by an image, was extended with a new language (French) and two new test sets. The multilingual image description task was changed such that at test time, only the image is given. Compared to last year, multimodal systems improved, but text-only systems remain competitive.

M3 - Conference contribution

SP - 215

EP - 233

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

PB - Association for Computational Linguistics

CY - Copenhagen, Denmark

T2 - Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description 2017

Y2 - 7 September 2017 through 8 September 2017

ER -

Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description

Abstract

Conference

Access to Document

Fingerprint

Cite this