Hamid Beigy


pdf bib
Persian Natural Language Inference: A Meta-learning Approach
Heydar Soudani | Mohammad Hassan Mojab | Hamid Beigy
Proceedings of the 29th International Conference on Computational Linguistics

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.


pdf bib
ParsTwiNER: A Corpus for Named Entity Recognition at Informal Persian
MohammadMahdi Aghajani | AliAkbar Badri | Hamid Beigy
Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)

As a result of unstructured sentences and some misspellings and errors, finding named entities in a noisy environment such as social media takes much more effort. ParsTwiNER contains about 250k tokens, based on standard instructions like MUC-6 or CoNLL 2003, gathered from Persian Twitter. Using Cohen’s Kappa coefficient, the consistency of annotators is 0.95, a high score. In this study, we demonstrate that some state-of-the-art models degrade on these corpora, and trained a new model using parallel transfer learning based on the BERT architecture. Experimental results show that the model works well in informal Persian as well as in formal Persian.