Semantically Enhanced Term Frequency based on Word Embeddings for Arabic Information Retrieval

Abstract : Traditional Information Retrieval (IR) models are based on bag-of-words paradigm, where relevance scores are computed based on exact matching of keywords. Although these models have already achieved good performance, it has been shown that most of dissatisfaction cases in relevance are due to term mismatch between queries and documents. In this paper, we introduce novel method to compute term frequency based on semantic similarities using distributed representations of words in a vector space (Word Embeddings). Our main goal is to allow distinct but semantically related terms to match each other and contribute to the relevance scores. Hence, Arabic documents are retrieved beyond the bag-of-words paradigm based on semantic similarities between word vectors. The results on Arabic standard TREC data sets show significant improvement over the baseline bag-of-words models.
Type de document :
Communication dans un congrès
Information Science and Technology (CIST), 2016 Fourth IEEE International Colloquium, Oct 2016, Tangier, Morocco. 〈http://www.ieee.ma/cist16/〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01409754
Contributeur : Abdelkader El Mahdaouy <>
Soumis le : mardi 6 décembre 2016 - 11:13:20
Dernière modification le : vendredi 21 juillet 2017 - 15:12:00

Identifiants

  • HAL Id : hal-01409754, version 1

Collections

Citation

Abdelkader El Mahdaouy, Saïd El Alaoui Ouatik, Eric Gaussier. Semantically Enhanced Term Frequency based on Word Embeddings for Arabic Information Retrieval. Information Science and Technology (CIST), 2016 Fourth IEEE International Colloquium, Oct 2016, Tangier, Morocco. 〈http://www.ieee.ma/cist16/〉. 〈hal-01409754〉

Partager

Métriques

Consultations de la notice

51