DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents

Gia-Hung Nguyen 1 Laure Soulier 2 Lynda Tamine 1 Nathalie Bricon-Souf 1
1 IRIT - Institut de recherche en informatique de Toulouse
2 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Tackling the vocabulary mismatch has been a long-standing and major goal in information retrieval. e state-of-the-art solutions mainly rely on leveraging either the relational semantics provided by external resources or the distributional semantics, recently investigated by deep neural approaches. Guided by the intuition that the relational semantics might improve the eeectiveness of deep neural approaches, we propose the Deep Semantic Resource Inference Model (DSRIM) that relies on a twofold contribution: 1) a representation of raw-data that models the relational semantics within text representations by jointly considering objects and relations expressed in a knowledge resource, and 2) an end-to-end neural architecture that jointly learns the query-document relevance and the combined distributional and relational semantic representation of documents and queries. e experimental evaluation is carried out on two TREC datasets from TREC Terabyte and TREC CDS tracks, and two diierent knowledge resources, respectively Word-Net and MeSH. e results indicate that knowledge resource-driven representations allow obtaining similar representations for similar documents while discriminating non-similar documents. Also, we show that our model outperforms state-of-the-art semantic and deep neural information retrieval models.
Keywords : Neural networks Ad-hoc IR knowledge resource semantic document representation deep neural architecture
Type de document :
Communication dans un congrès
International Conference on the Theory of Information Retrieval, Oct 2017, Amsterdam, Netherlands. The 3rd ACM International Conference on the Theory of Information Retrieval
Liste complète des métadonnées
https://hal.sorbonne-universite.fr/hal-01549543
Contributeur : Laure Soulier <>
Soumis le : mercredi 28 juin 2017 - 18:00:49
Dernière modification le : jeudi 22 novembre 2018 - 14:30:31
Document(s) archivé(s) le : jeudi 18 janvier 2018 - 03:20:48

Fichier

1706.04922.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01549543, version 1

Collections

UPMC | UNIV-TLSE3 | SMS | UNIV-TLSE2 | LIP6 | SORBONNE-UNIVERSITE

Citation

Gia-Hung Nguyen, Laure Soulier, Lynda Tamine, Nathalie Bricon-Souf. DSRIM: A Deep Neural Information Retrieval Model Enhanced by a Knowledge Resource Driven Representation of Documents. International Conference on the Theory of Information Retrieval, Oct 2017, Amsterdam, Netherlands. The 3rd ACM International Conference on the Theory of Information Retrieval. 〈hal-01549543〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

274

Téléchargements de fichiers

118

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD