Papers
arxiv:2409.09009

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

Published on Sep 13, 2024
Authors:
,
,

Abstract

A retrieval-and-demonstration approach enhances rare word translation accuracy in direct speech translation models by incorporating retrieved examples, improving performance with both gold and retrieved examples.

AI-generated summary

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 (https://github.com/SiqiLii/Retrieve-and-Demonstration-ST).

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2409.09009 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2409.09009 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2409.09009 in a Space README.md to link it from this page.

Collections including this paper 1