TY - GEN
T1 - How to Design Translation Prompts for ChatGPT
T2 - 6th ACM International Conference on Multimedia in Asia Workshops, MMAsia 2024 Workshops
AU - Gao, Yuan
AU - Wang, Ruili
AU - Hou, Feng
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s).
PY - 2024/12/26
Y1 - 2024/12/26
N2 - ChatGPT, a chatbot based on the GPT models, has demonstrated surprising abilities in natural language understanding and generation tasks. Given that machine translation heavily relies on these abilities, there is substantial promise in applying ChatGPT for machine translation. Using naive prompts cannot fully unleash ChatGPT’s translation ability. Thus, in this paper, we propose several translation prompts that contain (i). translation task information (e.g., English-to-German), (ii). context domain information (e.g., News), (iii). Part-of-Speech (POS) tags, respectively. Our experimental results show that our proposed translation prompts can significantly enhance ChatGPT’s translation performance. We evaluate the translation quality using multi-reference test sets which consist of ten different human translations for each source sentence, and ChatGPT achieves superior performance compared to commercial systems. In addition, we also develop few-shot prompts upon our proposed translation prompts, which consistently show improvement across different translation directions.
AB - ChatGPT, a chatbot based on the GPT models, has demonstrated surprising abilities in natural language understanding and generation tasks. Given that machine translation heavily relies on these abilities, there is substantial promise in applying ChatGPT for machine translation. Using naive prompts cannot fully unleash ChatGPT’s translation ability. Thus, in this paper, we propose several translation prompts that contain (i). translation task information (e.g., English-to-German), (ii). context domain information (e.g., News), (iii). Part-of-Speech (POS) tags, respectively. Our experimental results show that our proposed translation prompts can significantly enhance ChatGPT’s translation performance. We evaluate the translation quality using multi-reference test sets which consist of ten different human translations for each source sentence, and ChatGPT achieves superior performance compared to commercial systems. In addition, we also develop few-shot prompts upon our proposed translation prompts, which consistently show improvement across different translation directions.
KW - ChatGPT
KW - Neural Machine Translation
KW - Prompt Design
UR - http://www.scopus.com/inward/record.url?scp=85216536654&partnerID=8YFLogxK
U2 - 10.1145/3700410.3702123
DO - 10.1145/3700410.3702123
M3 - Conference contribution
AN - SCOPUS:85216536654
T3 - Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops, MMAsia 2024 Workshops
BT - Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops, MMAsia 2024 Workshops
PB - Association for Computing Machinery, Inc
Y2 - 3 December 2024 through 6 December 2024
ER -