Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language

Peter A. Jansen; Jordan Boyd-Graber

doi:10.18653/v1/2022.flp-1.5

Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language

Peter A. Jansen, Jordan Boyd-Graber

Information, School of

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

Abstract

Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as “Darmok and Jalad at Tanagra” instead of “We should work together.” This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. A machine translation system based on a large language model (T5) is trained using this parallel corpus, and is shown to produce an accuracy of 76% when translating from English to Tamarian on known utterances.

Original language	English (US)
Title of host publication	FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	34-38
Number of pages	5
ISBN (Electronic)	9781959429111
DOIs	https://doi.org/10.18653/v1/2022.flp-1.5
State	Published - 2022
Event	3rd Workshop on Figurative Language Processing, FigLang 2022, as part of EMNLP 2022 - Abu Dhabi, United Arab Emirates Duration: Dec 8 2022 → …

Publication series

Name	FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop

Conference

Conference	3rd Workshop on Figurative Language Processing, FigLang 2022, as part of EMNLP 2022
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	12/8/22 → …

ASJC Scopus subject areas

Language and Linguistics
Artificial Intelligence
Computer Science Applications
Linguistics and Language

Access to Document

10.18653/v1/2022.flp-1.5

Cite this

Jansen, P. A., & Boyd-Graber, J. (2022). Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language. In FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop (pp. 34-38). (FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.flp-1.5

Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language. / Jansen, Peter A.; Boyd-Graber, Jordan.
FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2022. p. 34-38 (FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop).

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

Jansen, PA & Boyd-Graber, J 2022, Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language. in FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop. FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 34-38, 3rd Workshop on Figurative Language Processing, FigLang 2022, as part of EMNLP 2022, Abu Dhabi, United Arab Emirates, 12/8/22. https://doi.org/10.18653/v1/2022.flp-1.5

Jansen PA, Boyd-Graber J. Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language. In FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2022. p. 34-38. (FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop). doi: 10.18653/v1/2022.flp-1.5

Jansen, Peter A. ; Boyd-Graber, Jordan. / Picard understanding Darmok : A Dataset and Model for Metaphor-Rich Translation in a Constructed Language. FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2022. pp. 34-38 (FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop).

@inproceedings{29fa032187a64d13834829abe96fd7a6,

title = "Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language",

abstract = "Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as “Darmok and Jalad at Tanagra” instead of “We should work together.” This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. A machine translation system based on a large language model (T5) is trained using this parallel corpus, and is shown to produce an accuracy of 76% when translating from English to Tamarian on known utterances.",

author = "Jansen, {Peter A.} and Jordan Boyd-Graber",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 3rd Workshop on Figurative Language Processing, FigLang 2022, as part of EMNLP 2022 ; Conference date: 08-12-2022",

year = "2022",

doi = "10.18653/v1/2022.flp-1.5",

language = "English (US)",

series = "FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop",

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

pages = "34--38",

booktitle = "FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop",

}

TY - GEN

T1 - Picard understanding Darmok

T2 - 3rd Workshop on Figurative Language Processing, FigLang 2022, as part of EMNLP 2022

AU - Jansen, Peter A.

AU - Boyd-Graber, Jordan

PY - 2022

Y1 - 2022

N2 - Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as “Darmok and Jalad at Tanagra” instead of “We should work together.” This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. A machine translation system based on a large language model (T5) is trained using this parallel corpus, and is shown to produce an accuracy of 76% when translating from English to Tamarian on known utterances.

AB - Tamarian, a fictional language introduced in the Star Trek episode Darmok, communicates meaning through utterances of metaphorical references, such as “Darmok and Jalad at Tanagra” instead of “We should work together.” This work assembles a Tamarian-English dictionary of utterances from the original episode and several follow-on novels, and uses this to construct a parallel corpus of 456 English-Tamarian utterances. A machine translation system based on a large language model (T5) is trained using this parallel corpus, and is shown to produce an accuracy of 76% when translating from English to Tamarian on known utterances.

UR - http://www.scopus.com/inward/record.url?scp=85153265977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85153265977&partnerID=8YFLogxK

U2 - 10.18653/v1/2022.flp-1.5

DO - 10.18653/v1/2022.flp-1.5

M3 - Conference contribution

AN - SCOPUS:85153265977

T3 - FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop

SP - 34

EP - 38

BT - FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

Y2 - 8 December 2022

ER -

Picard understanding Darmok: A Dataset and Model for Metaphor-Rich Translation in a Constructed Language

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this