International audiencePrevious work in information retrieval (IR) have shown that using evidence, such as concepts and relations, from external knowledge resources could enhance the retrieval performance. Recently, deep neural 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 representation learning to tackle a number of issues including polysemy and granularity mismatch. We show the effectiveness of the framework in various IR tasks including word similarity, document similarity, and document re-ranking. M...
This thesis work is in the fields of textual information retrieval (IR) and deep learning using neur...
A recent "third wave'' of neural network (NN) approaches now delivers state-of-the-art performance i...
Most neural Information Retrieval (Neu-IR) models derive query-to-document ranking scores based on t...
International audiencePrevious work in information retrieval (IR) have shown that using evidence, su...
International audiencePrevious work in information retrieval have shown that using evidence, such as...
In this thesis, we focus on bridging the semantic gap between the documents and queries representati...
Le projet de thèse porte sur l'application des approches neuronales pour la représentation de textes...
National audienceDe nombreux travaux en recherche d'information (RI) ont montré l'apport de la séman...
The semantic mismatch between query and document terms-i.e., the semantic gap-is a long-standing pro...
International audienceInformationRetrieval(IR)classicallyreliesonseveralprocessestoimproveperfor- ma...
International audienceRecent deep approaches to information retrieval are either representation-orie...
Recent advances in neural language models have contributed new methods for learning distributed vect...
Ad-hoc retrieval models can benefit from considering different patterns in the interactions between ...
International audienceThis paper tackles the problem of the semantic gap between a document and a qu...
The state-of-the-art solutions to the vocabulary mismatch in information retrieval (IR) mainly aim a...
This thesis work is in the fields of textual information retrieval (IR) and deep learning using neur...
A recent "third wave'' of neural network (NN) approaches now delivers state-of-the-art performance i...
Most neural Information Retrieval (Neu-IR) models derive query-to-document ranking scores based on t...
International audiencePrevious work in information retrieval (IR) have shown that using evidence, su...
International audiencePrevious work in information retrieval have shown that using evidence, such as...
In this thesis, we focus on bridging the semantic gap between the documents and queries representati...
Le projet de thèse porte sur l'application des approches neuronales pour la représentation de textes...
National audienceDe nombreux travaux en recherche d'information (RI) ont montré l'apport de la séman...
The semantic mismatch between query and document terms-i.e., the semantic gap-is a long-standing pro...
International audienceInformationRetrieval(IR)classicallyreliesonseveralprocessestoimproveperfor- ma...
International audienceRecent deep approaches to information retrieval are either representation-orie...
Recent advances in neural language models have contributed new methods for learning distributed vect...
Ad-hoc retrieval models can benefit from considering different patterns in the interactions between ...
International audienceThis paper tackles the problem of the semantic gap between a document and a qu...
The state-of-the-art solutions to the vocabulary mismatch in information retrieval (IR) mainly aim a...
This thesis work is in the fields of textual information retrieval (IR) and deep learning using neur...
A recent "third wave'' of neural network (NN) approaches now delivers state-of-the-art performance i...
Most neural Information Retrieval (Neu-IR) models derive query-to-document ranking scores based on t...