通过基于有限状态解码约束的分割将大语言模型用于长篇语音翻译
Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
AI总结：
针对长篇语音翻译难题，本研究通过有限状态解码约束调整大语言模型分割长ASR转录文本，有效克服幻觉，在9个测试集中将TED演讲翻译平均BLEU提升2.9分。
摘要：
语音翻译中的一个挑战是，大量口语内容是长篇的，但短单元对于获得高质量翻译是必要的。为了解决这种不匹配，我们调整大语言模型（LLMs）将长ASR转录文本分割成可独立翻译的片段，从而最大化整体翻译质量。我们通过在解码过程中引入有限状态约束来克服LLMs的幻觉倾向；这些约束消除了无效输出，且无需额外训练。我们发现LLMs能够通过提示微调或微调适应包含ASR错误的转录文本。与最先进的自动标点基线相比，我们最佳的LLM在9个测试集中，仅通过改进分割，就将英语-德语、英语-西班牙语和英语-阿拉伯语TED演讲翻译的平均BLEU提升了2.9分。
英文摘要：
One challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we adapt large language models (LLMs) to split long ASR transcripts into segments that can be independently translated so as to maximize the overall translation quality. We overcome the tendency of hallucination in LLMs by incorporating finite-state constraints during decoding; these eliminate invalid outputs without requiring additional training. We discover that LLMs are adaptable to transcripts containing ASR errors through prompt-tuning or fine-tuning. Relative to a state-of-the-art automatic punctuation baseline, our best LLM improves the average BLEU by 2.9 points for English-German, English-Spanish, and English-Arabic TED talk translation in 9 test sets, just by improving segmentation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
