Leveraging Discourse Structure for Extractive Meeting Summarization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rennard, Virgile, Shang, Guokan, Vazirgiannis, Michalis, Hunter, Julie
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916406500524032
author Rennard, Virgile
Shang, Guokan
Vazirgiannis, Michalis
Hunter, Julie
author_facet Rennard, Virgile
Shang, Guokan
Vazirgiannis, Michalis
Hunter, Julie
contents We introduce an extractive summarization system for meetings that leverages discourse structure to better identify salient information from complex multi-party discussions. Using discourse graphs to represent semantic relations between the contents of utterances in a meeting, we train a GNN-based node classification model to select the most important utterances, which are then combined to create an extractive summary. Experimental results on AMI and ICSI demonstrate that our approach surpasses existing text-based and graph-based extractive summarization systems, as measured by both classification and summarization metrics. Additionally, we conduct ablation studies on discourse structure and relation type to provide insights for future NLP applications leveraging discourse analysis theory.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11055
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging Discourse Structure for Extractive Meeting Summarization
Rennard, Virgile
Shang, Guokan
Vazirgiannis, Michalis
Hunter, Julie
Computation and Language
Artificial Intelligence
We introduce an extractive summarization system for meetings that leverages discourse structure to better identify salient information from complex multi-party discussions. Using discourse graphs to represent semantic relations between the contents of utterances in a meeting, we train a GNN-based node classification model to select the most important utterances, which are then combined to create an extractive summary. Experimental results on AMI and ICSI demonstrate that our approach surpasses existing text-based and graph-based extractive summarization systems, as measured by both classification and summarization metrics. Additionally, we conduct ablation studies on discourse structure and relation type to provide insights for future NLP applications leveraging discourse analysis theory.
title Leveraging Discourse Structure for Extractive Meeting Summarization
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.11055