Word confidence estimation for speech translation

L. Besacier, B. Lecouteux, N. Q. Luong, K. Hour, M. Hadjsalah


Abstract
Word Confidence Estimation (WCE) for machine translation (MT) or automatic speech recognition (ASR) consists in judging each word in the (MT or ASR) hypothesis as correct or incorrect by tagging it with an appropriate label. In the past, this task has been treated separately in ASR or MT contexts and we propose here a joint estimation of word confidence for a spoken language translation (SLT) task involving both ASR and MT. This research work is possible because we built a specific corpus which is first presented. This corpus contains 2643 speech utterances for which a quintuplet containing: ASR output (src-asr), verbatim transcript (src-ref), text translation output (tgt-mt), speech translation output (tgt-slt) and post-edition of translation (tgt-pe), is made available. The rest of the paper illustrates how such a corpus (made available to the research community) can be used for evaluating word confidence estimators in ASR, MT or SLT scenarios. WCE for SLT could help rescoring SLT output graphs, improving translators productivity (for translation of lectures or movie subtitling) or it could be useful in interactive speech-to-speech translation scenarios.
Anthology ID:
2014.iwslt-papers.3
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Papers
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
169–175
Language:
URL:
https://aclanthology.org/2014.iwslt-papers.3
DOI:
Bibkey:
Cite (ACL):
L. Besacier, B. Lecouteux, N. Q. Luong, K. Hour, and M. Hadjsalah. 2014. Word confidence estimation for speech translation. In Proceedings of the 11th International Workshop on Spoken Language Translation: Papers, pages 169–175, Lake Tahoe, California.
Cite (Informal):
Word confidence estimation for speech translation (Besacier et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-papers.3.pdf