Leveraging Discourse Structure for Extractive Meeting Summarization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| 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 |