On the Hallucination in Simultaneous Machine Translation

Meizhi Zhong, Kehai Chen, Zhengshan Xue, Lemao Liu, Mingming Yang, Min Zhang


Abstract
It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information. While many efforts have been made to enhance performance for SiMT, few of them attempt to understand and analyze hallucination in SiMT.Therefore, we conduct a comprehensive analysis of hallucination in SiMT from two perspectives: understanding the distribution of hallucination words and the target-side context usage of them.Intensive experiments demonstrate some valuable findings and particularly show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.
Anthology ID:
2024.acl-short.66
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
730–742
Language:
URL:
https://aclanthology.org/2024.acl-short.66
DOI:
Bibkey:
Cite (ACL):
Meizhi Zhong, Kehai Chen, Zhengshan Xue, Lemao Liu, Mingming Yang, and Min Zhang. 2024. On the Hallucination in Simultaneous Machine Translation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 730–742, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
On the Hallucination in Simultaneous Machine Translation (Zhong et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-short.66.pdf