Abstract
For the detection of personal tweets, where a parent speaks of a child’s birth defect, CLaC combines ELMo word embeddings and gazetteer lists from external resources with a GCNN (for encoding dependencies), in a multi layer, transformer inspired architecture. To address the task, we compile several gazetteer lists from resources such as MeSH and GI. The proposed system obtains .69 for μF1 score in the SMM4H 2020 Task 5 where the competition average is .65.- Anthology ID:
- 2020.smm4h-1.32
- Volume:
- Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Venue:
- SMM4H
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 168–170
- Language:
- URL:
- https://aclanthology.org/2020.smm4h-1.32
- DOI:
- Cite (ACL):
- Parsa Bagherzadeh and Sabine Bergler. 2020. CLaC at SMM4H 2020: Birth Defect Mention Detection. In Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task, pages 168–170, Barcelona, Spain (Online). Association for Computational Linguistics.
- Cite (Informal):
- CLaC at SMM4H 2020: Birth Defect Mention Detection (Bagherzadeh & Bergler, SMM4H 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.smm4h-1.32.pdf