Saved in:
Bibliographic Details
Main Authors: Kang, Jeongwoo, Vartampetian, Markarit, Herron, Felix, Zhou, Yongxin, Fabre, Diandra, Gonzalez-Saez, Gabriela
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.00476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915421753442304
author Kang, Jeongwoo
Vartampetian, Markarit
Herron, Felix
Zhou, Yongxin
Fabre, Diandra
Gonzalez-Saez, Gabriela
author_facet Kang, Jeongwoo
Vartampetian, Markarit
Herron, Felix
Zhou, Yongxin
Fabre, Diandra
Gonzalez-Saez, Gabriela
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2508_00476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 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
Computation and Language
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).
title GETALP@AutoMin 2025: Leveraging RAG to Answer Questions based on Meeting Transcripts
topic Computation and Language
url https://arxiv.org/abs/2508.00476