Neural Networks Revisited for Proper Name Retrieval from Diachronic Documents - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Neural Networks Revisited for Proper Name Retrieval from Diachronic Documents

Résumé

Developing high-quality transcription systems for very large vocabulary corpora is a challenging task. Proper names are usually key to understanding the information contained in a document. To increase the vocabulary coverage, a huge amount of text data should be used. In this paper, we extend the previously proposed neural networks for word embedding models: word vector representation proposed by Mikolov is enriched by an additional non-linear transformation. This model allows to better take into account lexical and semantic word relationships. In the context of broadcast news transcription and in terms of recall, experimental results show a good ability of the proposed model to select new relevant proper names.
Fichier principal
Vignette du fichier
ltc-009-illina.pdf (407.66 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01240480 , version 1 (10-12-2015)

Identifiants

  • HAL Id : hal-01240480 , version 1

Citer

Irina Illina, Dominique Fohr. Neural Networks Revisited for Proper Name Retrieval from Diachronic Documents. LTC Language & Technology Conference, Nov 2015, Poznan, Poland. pp.120-124. ⟨hal-01240480⟩
194 Consultations
237 Téléchargements

Partager

Gmail Facebook X LinkedIn More