Arabic Natural Language Processing from Software Engineering to Complex Pipeline

Jaafar, Younes; Bouzoubaa, Karim

doi:10.1109/acling.2015.11

Cited by 14 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We tackle this problem by conducting an extensive comparison of different stemming and lemmatisation approaches, coupled with four different IR models, from different families. In order to perform Arabic text lemmatisation, we used SAFAR API sentence splitter [50] to segment the collection’s documents and feed the obtained sentences to Farasa and MADAMIRA lemmatisation modules [46,45]. Since MADAMIRA lemmatiser produces vocalised lemmas, we used the SafeBW transliteration scheme of the underlying system in order to preserve diacritics representation for vocalised lemma-based indexing method (M vocL).…”

Section: Experimental Evaluationmentioning

confidence: 99%

Word-embedding-based pseudo-relevance feedback for Arabic information retrieval

Mahdaouy

Alaoui

Gaussier

2018

Journal of Information Science

View full text Add to dashboard Cite

Pseudo-relevance feedback (PRF) is a very effective query expansion approach, which reformulates queries by selecting expansion terms from top k pseudo-relevant documents. Although standard PRF models have been proven effective to deal with vocabulary mismatch between users’ queries and relevant documents, expansion terms are selected without considering their similarity to the original query terms. In this article, we propose a method to incorporate word embedding (WE) similarity into PRF models for Arabic information retrieval (IR). The main idea is to select expansion terms using their distribution in the set of top pseudo-relevant documents along with their similarity to the original query terms. Experiments are conducted on the standard Arabic TREC 2001/2002 collection using three neural WE models. The obtained results show that our PRF extensions significantly outperform their baseline PRF models. Moreover, they enhanced the baseline IR model by 22% and 68% for the mean average precision (MAP) and the robustness index (RI), respectively.

show abstract

Section: Experimental Evaluationmentioning

confidence: 99%

Word-embedding-based pseudo-relevance feedback for Arabic information retrieval

Mahdaouy

Alaoui

Gaussier

2018

Journal of Information Science

View full text Add to dashboard Cite

show abstract

“…However, as SAFAR (Y. Jaafar & Bouzoubaa, 2015) is written in Java, Tashaphyne was translated to the Java programming language to enable its integration into the framework.…”

Section: Statement Of Needmentioning

confidence: 99%

“…Tashaphyne has been widely used as a tool in various natural language processing tasks by researchers. Stemming development and evaluation have been explored by (Atoum & Nouman, 2019;Dahab et al, 2015;ElDefrawy et al, 2015bElDefrawy et al, , 2016Younes Jaafar et al, 2017;Y. Jaafar & Bouzoubaa, 2015).…”

Section: Mentionmentioning

confidence: 99%

Tashaphyne: A Python package for Arabic Light Stemming

Zerrouki

2024

JOSS

View full text Add to dashboard Cite

Stemming is an important task in natural language processing that involves reducing a word to its root form, or stem. In many cases, stemming can significantly improve the accuracy and efficiency of text analysis tasks such as information retrieval, text classification, and sentiment analysis. For the Arabic language, which has a rich morphology with a large number of prefixes and suffixes, stemming is particularly challenging. Tashaphyne provides an effective solution to this challenge, making it a valuable tool for researchers and practitioners working with Arabic text data.

show abstract

An Empirical Analysis of Moroccan Dialectal User-Generated Text

Tachicart

Bouzoubaa

2019

Computational Collective Intelligence

View full text Add to dashboard Cite

Arabic Natural Language Processing from Software Engineering to Complex Pipeline

Cited by 14 publications

References 7 publications

Word-embedding-based pseudo-relevance feedback for Arabic information retrieval

Word-embedding-based pseudo-relevance feedback for Arabic information retrieval

Tashaphyne: A Python package for Arabic Light Stemming

An Empirical Analysis of Moroccan Dialectal User-Generated Text

Contact Info

Product

Resources

About