GETALP@AutoMin 2025: Leveraging RAG to Answer Questions based on Meeting Transcripts
Kang, Jeongwoo, Vartampetian, Markarit, Herron, Felix, Zhou, Yongxin, Fabre, Diandra, Gonzalez-Saez, Gabriela
–arXiv.org Artificial Intelligence
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).
arXiv.org Artificial Intelligence
Aug-4-2025
- Country:
- Europe > France (0.29)
- North America > Mexico (0.28)
- Asia > Middle East
- UAE (0.28)
- Genre:
- Research Report > New Finding (1.00)
- Technology: