Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning

TL;DR

This paper introduces a novel nested embedding learning framework for Arabic NLP, demonstrating that language-specific Matryoshka models significantly improve semantic similarity understanding over traditional approaches.

Contribution

The work develops a new Arabic nested embedding framework using Matryoshka learning, with datasets translated into Arabic for comprehensive evaluation, showing superior performance in semantic similarity tasks.

Findings

Matryoshka embedding models outperform traditional models by 20-25%.

Models effectively capture Arabic-specific semantic nuances.

Evaluation across multiple metrics confirms improved performance.

Abstract

This work presents a novel framework for training Arabic nested embedding models through Matryoshka Embedding Learning, leveraging multilingual, Arabic-specific, and English-based models, to highlight the power of nested embeddings models in various Arabic NLP downstream tasks. Our innovative contribution includes the translation of various sentence similarity datasets into Arabic, enabling a comprehensive evaluation framework to compare these models across different dimensions. We trained several nested embedding models on the Arabic Natural Language Inference triplet dataset and assessed their performance using multiple evaluation metrics, including Pearson and Spearman correlations for cosine similarity, Manhattan distance, Euclidean distance, and dot product similarity. The results demonstrate the superior performance of the Matryoshka embedding models, particularly in capturing semantic nuances unique to the Arabic language. Results demonstrated that Arabic Matryoshka embedding models have superior performance in capturing semantic nuances unique to the Arabic language, significantly outperforming traditional models by up to 20-25\% across various similarity metrics. These results underscore the effectiveness of language-specific training and highlight the potential of Matryoshka models in enhancing semantic textual similarity tasks for Arabic NLP.