Enhanced Arabic Text Retrieval with Attentive Relevance Scoring

TL;DR

This paper introduces an improved Arabic-specific Dense Passage Retrieval framework utilizing a novel Attentive Relevance Scoring mechanism, which enhances semantic relevance modeling and significantly boosts retrieval accuracy for Arabic questions.

Contribution

It presents a new ARS method integrated with pre-trained Arabic models, tailored for better IR performance in Arabic NLP tasks.

Findings

Improved ranking accuracy in Arabic question answering.

Effective modeling of semantic relevance with ARS.

Enhanced retrieval performance over baseline models.

Abstract

Arabic poses a particular challenge for natural language processing (NLP) and information retrieval (IR) due to its complex morphology, optional diacritics and the coexistence of Modern Standard Arabic (MSA) and various dialects. Despite the growing global significance of Arabic, it is still underrepresented in NLP research and benchmark resources. In this paper, we present an enhanced Dense Passage Retrieval (DPR) framework developed specifically for Arabic. At the core of our approach is a novel Attentive Relevance Scoring (ARS) that replaces standard interaction mechanisms with an adaptive scoring function that more effectively models the semantic relevance between questions and passages. Our method integrates pre-trained Arabic language models and architectural refinements to improve retrieval performance and significantly increase ranking accuracy when answering Arabic questions. The code is made publicly available at \href{https://github.com/Bekhouche/APR}{GitHub}.