Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach

Siqi Li, Danni Liu, Jan Niehues


Abstract
Direct speech translation (ST) models often struggle with rare words. Incorrect translation of these words can have severe consequences, impacting translation quality and user trust. While rare word translation is inherently challenging for neural models due to sparse learning signals, real-world scenarios often allow access to translations of past recordings on similar topics. To leverage these valuable resources, we propose a retrieval-and-demonstration approach to enhance rare word translation accuracy in direct ST models. First, we adapt existing ST models to incorporate retrieved examples for rare word translation, which allows the model to benefit from prepended examples, similar to in-context learning. We then develop a cross-modal (speech-to-speech, speech-to-text, text-to-text) retriever to locate suitable examples. We demonstrate that standard ST models can be effectively adapted to leverage examples for rare word translation, improving rare word translation accuracy over the baseline by 17.6% with gold examples and 8.5% with retrieved examples. Moreover, our speech-to-speech retrieval approach outperforms other modalities and exhibits higher robustness to unseen speakers. Our code is publicly available.
Anthology ID:
2024.emnlp-main.708
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12703–12719
Language:
URL:
https://aclanthology.org/2024.emnlp-main.708
DOI:
Bibkey:
Cite (ACL):
Siqi Li, Danni Liu, and Jan Niehues. 2024. Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12703–12719, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach (Li et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.708.pdf
Software:
 2024.emnlp-main.708.software.zip