Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering

Seungjun Lee; Hyeonseok Moon; Chanjun Park; Heuiseok Lim

doi:10.18653/v1/2023.iwslt-1.40

Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering

Seungjun Lee, Hyeonseok Moon, Chanjun Park, Heuiseok Lim

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

6 Citations (Scopus)

Abstract

In this paper, we present the KU x Upstage team’s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with diverse grammatical formality markers. Our methodology comprises two primary components: 1) a language-specific data-driven approach, and 2) the generation of synthetic data through the employment of large-scale language models and empirically-grounded prompt engineering. By adapting methodologies and models to accommodate the unique linguistic properties of each language, we observe a notable enhancement in performance relative to the baseline, substantiating the heightened efficacy of data-driven approaches. Moreover, our devised prompt engineering strategy yields superior synthetic translation instances.

Original language	English
Title of host publication	20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference
Editors	Elizabeth Salesky, Marcello Federico, Marine Carpuat
Publisher	Association for Computational Linguistics
Pages	420-432
Number of pages	13
ISBN (Electronic)	9781959429845
DOIs	https://doi.org/10.18653/v1/2023.iwslt-1.40
Publication status	Published - 2023
Event	20th International Conference on Spoken Language Translation, IWSLT 2023 - Hybrid, Toronto, Canada Duration: 2023 Jul 13 → 2023 Jul 14

Publication series

Name	20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

Conference

Conference	20th International Conference on Spoken Language Translation, IWSLT 2023
Country/Territory	Canada
City	Hybrid, Toronto
Period	23/7/13 → 23/7/14

Bibliographical note

Publisher Copyright:
© IWSLT 2023.All rights reserved.

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Linguistics and Language

Access to Document

10.18653/v1/2023.iwslt-1.40

Cite this

Lee, S., Moon, H., Park, C., & Lim, H. (2023). Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering. In E. Salesky, M. Federico, & M. Carpuat (Eds.), 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference (pp. 420-432). (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.iwslt-1.40

Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering. / Lee, Seungjun; Moon, Hyeonseok; Park, Chanjun et al.
20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. ed. / Elizabeth Salesky; Marcello Federico; Marine Carpuat. Association for Computational Linguistics, 2023. p. 420-432 (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference).

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

Lee, S, Moon, H, Park, C & Lim, H 2023, Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering. in E Salesky, M Federico & M Carpuat (eds), 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference, Association for Computational Linguistics, pp. 420-432, 20th International Conference on Spoken Language Translation, IWSLT 2023, Hybrid, Toronto, Canada, 23/7/13. https://doi.org/10.18653/v1/2023.iwslt-1.40

Lee S, Moon H, Park C, Lim H. Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering. In Salesky E, Federico M, Carpuat M, editors, 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. Association for Computational Linguistics. 2023. p. 420-432. (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference). doi: 10.18653/v1/2023.iwslt-1.40

Lee, Seungjun ; Moon, Hyeonseok ; Park, Chanjun et al. / Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering. 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference. editor / Elizabeth Salesky ; Marcello Federico ; Marine Carpuat. Association for Computational Linguistics, 2023. pp. 420-432 (20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference).

@inproceedings{0e5378f6e55d4b6eb2866e44eac95926,

title = "Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering",

abstract = "In this paper, we present the KU x Upstage team{\textquoteright}s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with diverse grammatical formality markers. Our methodology comprises two primary components: 1) a language-specific data-driven approach, and 2) the generation of synthetic data through the employment of large-scale language models and empirically-grounded prompt engineering. By adapting methodologies and models to accommodate the unique linguistic properties of each language, we observe a notable enhancement in performance relative to the baseline, substantiating the heightened efficacy of data-driven approaches. Moreover, our devised prompt engineering strategy yields superior synthetic translation instances.",

author = "Seungjun Lee and Hyeonseok Moon and Chanjun Park and Heuiseok Lim",

note = "Publisher Copyright: {\textcopyright} IWSLT 2023.All rights reserved.; 20th International Conference on Spoken Language Translation, IWSLT 2023 ; Conference date: 13-07-2023 Through 14-07-2023",

year = "2023",

doi = "10.18653/v1/2023.iwslt-1.40",

language = "English",

series = "20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference",

publisher = "Association for Computational Linguistics",

pages = "420--432",

editor = "Elizabeth Salesky and Marcello Federico and Marine Carpuat",

booktitle = "20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference",

}

TY - GEN

T1 - Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering

AU - Lee, Seungjun

AU - Moon, Hyeonseok

AU - Park, Chanjun

AU - Lim, Heuiseok

PY - 2023

Y1 - 2023

N2 - In this paper, we present the KU x Upstage team’s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with diverse grammatical formality markers. Our methodology comprises two primary components: 1) a language-specific data-driven approach, and 2) the generation of synthetic data through the employment of large-scale language models and empirically-grounded prompt engineering. By adapting methodologies and models to accommodate the unique linguistic properties of each language, we observe a notable enhancement in performance relative to the baseline, substantiating the heightened efficacy of data-driven approaches. Moreover, our devised prompt engineering strategy yields superior synthetic translation instances.

AB - In this paper, we present the KU x Upstage team’s submission for the Special Task on Formality Control on Spoken Language Translation, which involves translating English into four languages with diverse grammatical formality markers. Our methodology comprises two primary components: 1) a language-specific data-driven approach, and 2) the generation of synthetic data through the employment of large-scale language models and empirically-grounded prompt engineering. By adapting methodologies and models to accommodate the unique linguistic properties of each language, we observe a notable enhancement in performance relative to the baseline, substantiating the heightened efficacy of data-driven approaches. Moreover, our devised prompt engineering strategy yields superior synthetic translation instances.

UR - http://www.scopus.com/inward/record.url?scp=85172435087&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.iwslt-1.40

DO - 10.18653/v1/2023.iwslt-1.40

M3 - Conference contribution

AN - SCOPUS:85172435087

T3 - 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

SP - 420

EP - 432

BT - 20th International Conference on Spoken Language Translation, IWSLT 2023 - Proceedings of the Conference

A2 - Salesky, Elizabeth

A2 - Federico, Marcello

A2 - Carpuat, Marine

PB - Association for Computational Linguistics

T2 - 20th International Conference on Spoken Language Translation, IWSLT 2023

Y2 - 13 July 2023 through 14 July 2023

ER -

Improving Formality-Sensitive Machine Translation using Data-Centric Approaches and Prompt Engineering

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this