Target Concept Guided Medical Concept Normalization in Noisy User-Generated Texts

Abstract

Medical concept normalization (MCN) i.e., mapping of colloquial medical phrases to standard concepts is an essential step in analysis of medical social media text. The main drawback in existing state-of-the-art approach (Kalyan and Sangeetha, 2020b) is learning target concept vector representations from scratch which requires more training instances. Our model is based on RoBERTa and target concept embeddings. In our model, we integrate a) target concept information in the form of target concept vectors generated by encoding target concept descriptions using SRoBERTa, state-of-the-art RoBERTa based sentence embedding model and b) domain lexicon knowledge by enriching target concept vectors with synonym relationship knowledge using retrofitting algorithm. It is the first attempt in MCN to exploit both target concept information as well as domain lexicon knowledge in the form of retrofitted target concept vectors. Our model outperforms all the existing models with an accuracy improvement up to 1.36% on three standard datasets. Further, our model when trained only on mapping lexicon synonyms achieves up to 4.87% improvement in accuracy.

Medical Concept Mention Identification in Social Media Posts using a Small Number of Sample References

“…Our proposed model to automatically identify the mentions of a set of medical concepts from the social media text is inspired by the medical concept normalization model proposed by Kalyan and Sangeetha (2020). The proposed model utilizes a small number of preselected positive and negative samples along with the name and synonyms of the medical concepts to learn an anchor vector representation (distributed representation) of each of these concepts.…”