Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MedScore: Factuality Evaluation of Free-Form Medical Answers
ARGUS: Hallucination and Omission Evaluation in Video-LLMs
Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation
UNCLE: Uncertainty Expressions in Long-Form Generation
Granary: Speech Recognition and Translation Dataset in 25 European Languages
Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.