Enhanced Arabic Text Retrieval with Attentive Relevance Scoring
This addresses the problem of underrepresentation and performance gaps in Arabic NLP and IR, offering a domain-specific solution with incremental improvements.
The paper tackles the challenge of Arabic text retrieval by developing an enhanced Dense Passage Retrieval framework with a novel Attentive Relevance Scoring mechanism, resulting in significantly improved ranking accuracy for Arabic question answering.
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}.