conftrace_

2022 COLING COLING 2022

IAI @ SocialDisNER : Catch me if you can! Capturing complex disease mentions in tweets

Abstract

AbstractBiomedical NER is an active research area today. Despite the availability of state-of-the-art models for standard NER tasks, their performance degrades on biomedical data due to OOV entities and the challenges encountered in specialized domains. We use Flair-NER framework to investigate the effectiveness of various contextual and static embeddings for NER on Spanish tweets, in particular, to capture complex disease mentions.

Authors

Aman Sinha, Cristina Garcia Holgado, Marianne Clausel, Matthieu Constant

Topics

Machine Learning > Core Methods > Classification Machine Learning > Application Areas > Domain Adaptation Deep Learning > Techniques > Model Architecture

Keywords

social media analysis named entity recognition disease detection biomedical text contextual embedding

More from COLING 2022

All COLING 2022 papers →

mattica@SMM4H’22: Leveraging sentiment for stance & premise joint learning

KU_ED at SocialDisNER: Extracting Disease Mentions in Tweets Written in Spanish

CHAAI@SMM4H’22: RoBERTa, GPT-2 and Sampling - An interesting concoction

UCCNLP@SMM4H’22:Label distribution aware long-tailed learning with post-hoc posterior calibration applied to text classification

HaleLab_NITK@SMM4H’22: Adaptive Learning Model for Effective Detection, Extraction and Normalization of Adverse Drug Events from Social Media Data

Yet@SMM4H’22: Improved BERT-based classification models with Rdrop and PolyLoss