Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks

TL;DR

This paper introduces Swan, a family of Arabic-centric embedding models, and ArabicMTEB, a comprehensive benchmark suite, demonstrating state-of-the-art performance and cultural awareness in Arabic NLP tasks.

Contribution

The paper presents Swan models tailored for Arabic, along with a new benchmark suite, ArabicMTEB, for evaluating cross-lingual and cultural performance, advancing Arabic NLP research.

Findings

Swan-Large outperforms Multilingual-E5-large on Arabic tasks.

Swan-Small surpasses Multilingual-E5-base in Arabic embeddings.

Models are dialectally and culturally aware, excelling across diverse Arabic domains.

Abstract

We introduce {\bf Swan}, a family of embedding models centred around the Arabic language, addressing both small-scale and large-scale use cases. Swan includes two variants: Swan-Small, based on ARBERTv2, and Swan-Large, built on ArMistral, a pretrained Arabic large language model. To evaluate these models, we propose ArabicMTEB, a comprehensive benchmark suite that assesses cross-lingual, multi-dialectal, multi-domain, and multi-cultural Arabic text embedding performance, covering eight diverse tasks and spanning 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilingual-E5-large in most Arabic tasks, while the Swan-Small consistently surpasses Multilingual-E5-base. Our extensive evaluations demonstrate that Swan models are both dialectally and culturally aware, excelling across various Arabic domains while offering significant monetary efficiency. This work significantly advances the field of Arabic language modelling and provides valuable resources for future research and applications in Arabic natural language processing. Our models and benchmark are available at our GitHub page: \href{https://github.com/UBC-NLP/swan}{https://github.com/UBC-NLP/swan}