Abstract
Named entity recognition (e.g., disease mention extraction) is one of the most relevant tasks for data mining in the medical field. Although it is a well-known challenge, the bulk of the efforts to tackle this task have been made using clinical texts commonly written in English. In this work, we present our contribution to the SocialDisNER competition, which consists of a transfer learning approach to extracting disease mentions in a corpus from Twitter written in Spanish. We fine-tuned a model based on mBERT and applied post-processing using regular expressions to propagate the entities identified by the model and enhance disease mention extraction. Our system achieved a competitive strict F1 of 0.851 on the testing data set.- Anthology ID:
- 2022.smm4h-1.6
- Volume:
- Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- SMM4H
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 19–22
- Language:
- URL:
- https://aclanthology.org/2022.smm4h-1.6
- DOI:
- Cite (ACL):
- Antonio Tamayo, Alexander Gelbukh, and Diego Burgos. 2022. NLP-CIC-WFU at SocialDisNER: Disease Mention Extraction in Spanish Tweets Using Transfer Learning and Search by Propagation. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 19–22, Gyeongju, Republic of Korea. Association for Computational Linguistics.
- Cite (Informal):
- NLP-CIC-WFU at SocialDisNER: Disease Mention Extraction in Spanish Tweets Using Transfer Learning and Search by Propagation (Tamayo et al., SMM4H 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.smm4h-1.6.pdf