A Tri-Partite Neural Document Language Model for Semantic Information Retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

A Tri-Partite Neural Document Language Model for Semantic Information Retrieval

Abstract

Previous work in information retrieval have shown that using evidence, such as concepts and relations, from external knowledge resources could enhance the retrieval performance. Recently, deep neu-ral approaches have emerged as state-of-the art models for capturing word semantics that can also be efficiently injected in IR models. This paper presents a new tri-partite neural document language framework that leverages explicit knowledge to jointly constrain word, concept, and document learning representations to tackle a number of issues including polysemy and granularity mismatch. We show the effectiveness of the framework in various IR tasks including document similarity, document re-ranking, and query expansion.
Fichier principal
Vignette du fichier
A_Tri-Partite_Neural_Document_Language_Model_for_Semantic_Information_Retrieval.pdf (402.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01841594 , version 1 (17-07-2018)
hal-01841594 , version 2 (07-06-2019)

Identifiers

Cite

Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf. A Tri-Partite Neural Document Language Model for Semantic Information Retrieval. ESWC 2018 - 15th European Semantic Web Conference, Jun 2018, Heraklion, Crète, Greece. pp.445-461, ⟨10.1007/978-3-319-93417-4_29⟩. ⟨hal-01841594v2⟩
197 View
335 Download

Altmetric

Share

Gmail Facebook X LinkedIn More