用词典增强语音翻译，提升短语翻译准确率
PHRASED: Phrase Dictionary Biasing for Speech Translation
- 引入源目标语言短语映射词典，引导模型翻译
- 流式模型相对提升21%，多模态大模型短语召回率提升85%
- 适合需要精准翻译术语或专业表达的场景
短语是理解对话核心概念的关键，但因训练数据中出现频率低，语音翻译任务中正确翻译短语极具挑战。本文提出一种短语词典偏置方法，利用源语言到目标语言的短语对应关系来增强翻译。该方法应用于两类主流模型：基于转换器的流式语音翻译模型和多模态大语言模型。实验表明，相比短语列表偏置，流式模型性能相对提升21%；多模态大语言模型在使用外部短语信息时，短语召回率提升85%。
原文摘要 · Abstract (English)
Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in speech translation tasks. In this paper, we propose a phrase dictionary biasing method to leverage pairs of phrases mapping from the source language to the target language. We apply the phrase dictionary biasing method to two types of widely adopted models, a transducer-based streaming speech translation model and a multimodal large language model. Experimental results show that the phrase dictionary biasing method outperforms phrase list biasing by 21% relatively for the streaming speech translation model. In addition, phrase dictionary biasing enables multimodal large language models to use external phrase information, achieving 85% relative improvement in phrase recall.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。