Persian Natural Language Inference: A Meta-learning approach
This work addresses natural language processing for low-resource languages like Persian, but it is incremental as it builds on existing multilingual and meta-learning techniques.
The paper tackles natural language inference for Persian, a low-resource language, by proposing a meta-learning approach that incorporates information from other languages and tasks, resulting in an accuracy improvement of roughly six percent over the baseline.
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.