A meaningful information extraction system for interactive analysis of documents - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

A meaningful information extraction system for interactive analysis of documents

Résumé

This paper is related to a project aiming at discovering weak signals from different streams of information, possibly sent by whistleblowers. The study presented in this paper tackles the particular problem of clustering topics at multi-levels from multiple documents, and then extracting meaningful descriptors, such as weighted lists of words for document representations in a multi-dimensions space. In this context, we present a novel idea which combines Latent Dirichlet Allocation and Word2vec (providing a consistency metric regarding the partitioned topics) as potential method for limiting the "a priori" number of cluster K usually needed in classical partitioning approaches. We proposed 2 implementations of this idea, respectively able to: (1) finding the best K for LDA in terms of topic consistency; (2) gathering the optimal clusters from different levels of clustering. We also proposed a non-traditional visualization approach based on a multi-agents system which combines both dimension reduction and interactivity.
Fichier principal
Vignette du fichier
PID6008627.pdf (1.25 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02552437 , version 1 (23-04-2020)

Identifiants

Citer

Julien Maitre, Michel Ménard, Guillaume Chiron, Alain Bouju, Nicolas Sidère. A meaningful information extraction system for interactive analysis of documents. International Conference on Document Analysis and Recognition (ICDAR 2019), Sep 2019, Sydney, Australia. pp.92-99, ⟨10.1109/ICDAR.2019.00024⟩. ⟨hal-02552437⟩

Collections

L3I UNIV-ROCHELLE
53 Consultations
250 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More