Toward a Deep Neural Approach for Knowledge-Based IR - Sorbonne Université Access content directly
Conference Papers Year : 2016

Toward a Deep Neural Approach for Knowledge-Based IR


This paper tackles the problem of the semantic gap between a document and a query within an ad-hoc information retrieval task. In this context, knowledge bases (KBs) have already been acknowledged as valuable means since they allow the representation of explicit relations between entities. However, they do not necessarily represent implicit relations that could be hidden in a corpora. This latter issue is tackled by recent works dealing with deep representation learning of texts. With this in mind, we argue that embedding KBs within deep neural architectures supporting document-query matching would give rise to fine-grained latent representations of both words and their semantic relations. In this paper, we review the main approaches of neural-based document ranking as well as those approaches for latent representation of entities and relations via KBs. We then propose some avenues to incorporate KBs in deep neural approaches for document ranking. More particularly, this paper advocates that KBs can be used either to support enhanced latent representations of queries and documents based on both distributional and relational semantics or to serve as a semantic translator between their latent distributional representations.
Fichier principal
Vignette du fichier
NeuIR.pdf (244.86 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01348993 , version 1 (26-07-2016)


  • HAL Id : hal-01348993 , version 1


Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf. Toward a Deep Neural Approach for Knowledge-Based IR. Workshop on Neural Information Retrieval during the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2016), Jul 2016, Pise, Italy. ⟨hal-01348993⟩
100 View
127 Download


Gmail Mastodon Facebook X LinkedIn More