Abstract
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.- Anthology ID:
- 2021.wnut-1.16
- Volume:
- Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 131–136
- Language:
- URL:
- https://aclanthology.org/2021.wnut-1.16
- DOI:
- 10.18653/v1/2021.wnut-1.16
- Cite (ACL):
- MohammadMahdi Aghajani, AliAkbar Badri, and Hamid Beigy. 2021. ParsTwiNER: A Corpus for Named Entity Recognition at Informal Persian. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 131–136, Online. Association for Computational Linguistics.
- Cite (Informal):
- ParsTwiNER: A Corpus for Named Entity Recognition at Informal Persian (Aghajani et al., WNUT 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.wnut-1.16.pdf
- Code
- overfit-ir/parstwiner
- Data
- ParsTwiner, CoNLL 2003, PEYMA