In this paper, we describe the development of a communication support system that detects erroneous translations to facilitate crosslingual communications due to the limitations of current machine chat translation methods. We trained an error detector as the baseline of the system and constructed a new Japanese-English bilingual chat corpus, BPersona-chat, which comprises multiturn colloquial chats augmented with crowdsourced quality ratings. The error detector can serve as an encouraging foundation for more advanced erroneous translation detection systems.
@article{arxiv.2308.01044,
title = {Chat Translation Error Detection for Assisting Cross-lingual Communications},
author = {Yunmeng Li and Jun Suzuki and Makoto Morishita and Kaori Abe and Ryoko Tokuhisa and Ana Brassard and Kentaro Inui},
journal= {arXiv preprint arXiv:2308.01044},
year = {2023}
}