Non-Parametric Memory Guidance for Multi-Document Summarization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Non-Parametric Memory Guidance for Multi-Document Summarization

Résumé

Multi-document summarization (MDS) is a difficult task in Natural Language Processing, aiming to summarize information from several documents. However, the source documents are often insufficient to obtain a qualitative summary. We propose a retriever-guided model combined with non-parametric memory for summary generation. This model retrieves relevant candidates from a database and then generates the summary considering the candidates with a copy mechanism and the source documents. The retriever is implemented with Approximate Nearest Neighbor Search (ANN) to search large databases. Our method is evaluated on the MultiXScience dataset which includes scientific articles. Finally, we discuss our results and possible directions for future work.
Fichier principal
Vignette du fichier
2023.ranlp-1.17.pdf (273.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04281841 , version 1 (13-11-2023)

Identifiants

Citer

Florian Baud, Alex Aussem. Non-Parametric Memory Guidance for Multi-Document Summarization. International Conference Recent Advances in Natural Language Processing (RANLP), Sep 2023, Varna, Bulgaria. ⟨hal-04281841⟩
24 Consultations
13 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More