An attentional model for speech translation without transcription

Long Duong; Antonios Anastasopoulos; David Chiang; Steven Bird; Trevor Cohn

doi:10.18653/v1/n16-1109

An attentional model for speech translation without transcription

Long Duong, Antonios Anastasopoulos, David Chiang, Steven Bird, Trevor Cohn

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

128 Citations (Scopus)

68 Downloads (Pure)

Abstract

For many low-resource languages, spoken language resources are more likely to be annotated with translations than transcriptions. This bilingual speech data can be used for word-spotting, spoken document retrieval, and even for documentation of endangered languages. We experiment with the neural, attentional model applied to this data. On phoneto-word alignment and translation reranking tasks, we achieve large improvements relative to several baselines. On the more challenging speech-to-word alignment task, our model nearly matches GIZA++'s performance on gold transcriptions, but without recourse to transcriptions or to a lexicon.

Original language	English
Title of host publication	2016 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
Editors	Kevin Knight, Ani Nenkova, Owen Rambow
Place of Publication	Pensylvannia
Publisher	Association for Computational Linguistics (ACL)
Pages	949-959
Number of pages	11
Volume	1
ISBN (Electronic)	9781941643914
DOIs	https://doi.org/10.18653/v1/n16-1109
Publication status	Published - Jun 2016
Externally published	Yes
Event	15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - San Diego, United States Duration: 12 Jun 2016 → 17 Jun 2016

Conference

Conference	15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
Country/Territory	United States
City	San Diego
Period	12/06/16 → 17/06/16

Access to Document

10.18653/v1/n16-1109

20905012-oaFinal published version, 316 KBLicence: CC BY

Cite this

Duong, L., Anastasopoulos, A., Chiang, D., Bird, S., & Cohn, T. (2016). An attentional model for speech translation without transcription. In K. Knight, A. Nenkova, & O. Rambow (Eds.), 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference (Vol. 1, pp. 949-959). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/n16-1109

Duong, Long ; Anastasopoulos, Antonios ; Chiang, David et al. / An attentional model for speech translation without transcription. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. editor / Kevin Knight ; Ani Nenkova ; Owen Rambow. Vol. 1 Pensylvannia : Association for Computational Linguistics (ACL), 2016. pp. 949-959

@inproceedings{76f36befa076433fb56cd1c34d4ee2c0,

title = "An attentional model for speech translation without transcription",

abstract = "For many low-resource languages, spoken language resources are more likely to be annotated with translations than transcriptions. This bilingual speech data can be used for word-spotting, spoken document retrieval, and even for documentation of endangered languages. We experiment with the neural, attentional model applied to this data. On phoneto-word alignment and translation reranking tasks, we achieve large improvements relative to several baselines. On the more challenging speech-to-word alignment task, our model nearly matches GIZA++'s performance on gold transcriptions, but without recourse to transcriptions or to a lexicon.",

author = "Long Duong and Antonios Anastasopoulos and David Chiang and Steven Bird and Trevor Cohn",

year = "2016",

month = jun,

doi = "10.18653/v1/n16-1109",

language = "English",

volume = "1",

pages = "949--959",

editor = "Kevin Knight and Ani Nenkova and Owen Rambow",

booktitle = "2016 Conference of the North American Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

note = "15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 ; Conference date: 12-06-2016 Through 17-06-2016",

}

Duong, L, Anastasopoulos, A, Chiang, D, Bird, S & Cohn, T 2016, An attentional model for speech translation without transcription. in K Knight, A Nenkova & O Rambow (eds), 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. vol. 1, Association for Computational Linguistics (ACL), Pensylvannia, pp. 949-959, 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016, San Diego, United States, 12/06/16. https://doi.org/10.18653/v1/n16-1109

An attentional model for speech translation without transcription. / Duong, Long; Anastasopoulos, Antonios; Chiang, David et al.
2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. ed. / Kevin Knight; Ani Nenkova; Owen Rambow. Vol. 1 Pensylvannia: Association for Computational Linguistics (ACL), 2016. p. 949-959.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

TY - GEN

T1 - An attentional model for speech translation without transcription

AU - Duong, Long

AU - Anastasopoulos, Antonios

AU - Chiang, David

AU - Bird, Steven

AU - Cohn, Trevor

PY - 2016/6

Y1 - 2016/6

N2 - For many low-resource languages, spoken language resources are more likely to be annotated with translations than transcriptions. This bilingual speech data can be used for word-spotting, spoken document retrieval, and even for documentation of endangered languages. We experiment with the neural, attentional model applied to this data. On phoneto-word alignment and translation reranking tasks, we achieve large improvements relative to several baselines. On the more challenging speech-to-word alignment task, our model nearly matches GIZA++'s performance on gold transcriptions, but without recourse to transcriptions or to a lexicon.

AB - For many low-resource languages, spoken language resources are more likely to be annotated with translations than transcriptions. This bilingual speech data can be used for word-spotting, spoken document retrieval, and even for documentation of endangered languages. We experiment with the neural, attentional model applied to this data. On phoneto-word alignment and translation reranking tasks, we achieve large improvements relative to several baselines. On the more challenging speech-to-word alignment task, our model nearly matches GIZA++'s performance on gold transcriptions, but without recourse to transcriptions or to a lexicon.

UR - https://www.scopus.com/pages/publications/84994162838

UR - http://m-mitchell.com/NAACL-2016/NAACL-HLT2016/

U2 - 10.18653/v1/n16-1109

DO - 10.18653/v1/n16-1109

M3 - Conference Paper published in Proceedings

AN - SCOPUS:84994162838

VL - 1

SP - 949

EP - 959

BT - 2016 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Knight, Kevin

A2 - Nenkova, Ani

A2 - Rambow, Owen

PB - Association for Computational Linguistics (ACL)

CY - Pensylvannia

T2 - 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016

Y2 - 12 June 2016 through 17 June 2016

ER -

Duong L, Anastasopoulos A, Chiang D, Bird S, Cohn T. An attentional model for speech translation without transcription. In Knight K, Nenkova A, Rambow O, editors, 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Vol. 1. Pensylvannia: Association for Computational Linguistics (ACL). 2016. p. 949-959 doi: 10.18653/v1/n16-1109

An attentional model for speech translation without transcription

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this