Persian Natural Language Inference: A Meta-learning approach

TL;DR

This paper introduces a meta-learning approach for Persian natural language inference that leverages multilingual data and task augmentation, achieving significant accuracy improvements over baseline methods.

Contribution

It proposes a novel meta-learning framework that combines multilingual transfer learning with task augmentation for low-resource Persian NLP tasks.

Findings

The proposed model outperforms baseline by approximately 6% accuracy.

Meta-learning with multilingual data improves low-resource NLP performance.

Task augmentation enhances the quality of training tasks.

Abstract

Incorporating information from other languages can improve the results of tasks in low-resource languages. A powerful method of building functional natural language processing systems for low-resource languages is to combine multilingual pre-trained representations with cross-lingual transfer learning. In general, however, shared representations are learned separately, either across tasks or across languages. This paper proposes a meta-learning approach for inferring natural language in Persian. Alternately, meta-learning uses different task information (such as QA in Persian) or other language information (such as natural language inference in English). Also, we investigate the role of task augmentation strategy for forming additional high-quality tasks. We evaluate the proposed method using four languages and an auxiliary task. Compared to the baseline approach, the proposed model consistently outperforms it, improving accuracy by roughly six percent. We also examine the effect of finding appropriate initial parameters using zero-shot evaluation and CCA similarity.