用检索增强生成与语义表示结合，提升会议记录问答准确率。
GETALP@AutoMin 2025: Leveraging RAG to Answer Questions based on Meeting Transcripts
- 融合RAG与抽象意义表示（AMR）进行问答
- 35%问题获得高质量回答，参会者区分类问题显著改善
- 适合需要精准理解会议对话的场景
本文记录了GETALP在SIGDial 2025第三届自动会议纪要共享任务中的参赛情况。我们参与了基于会议转录文本的问答任务（Task B）。方法基于检索增强生成（RAG）系统与抽象意义表示（AMR）。提出三种结合这两种技术的系统。结果表明，引入AMR使约35%的问题获得高质量回答，并在涉及区分不同参会者（如“谁提问”）的问题上表现显著提升。
原文摘要 · Abstract (English)
This paper documents GETALP's submission to the Third Run of the Automatic Minuting Shared Task at SIGDial 2025. We participated in Task B: question-answering based on meeting transcripts. Our method is based on a retrieval augmented generation (RAG) system and Abstract Meaning Representations (AMR). We propose three systems combining these two approaches. Our results show that incorporating AMR leads to high-quality responses for approximately 35% of the questions and provides notable improvements in answering questions that involve distinguishing between different participants (e.g., who questions).
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。