Normalising Medical Concepts in Social Media Texts by Learning Semantic Representation

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1014–1023, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Normalising Medical Concepts in Social Media Texts by Learning Semantic Representation Nut Limsopatham and Nigel Collier Language Technology Lab Department of Theoretical and Applied Linguistics University of Cambridge Cambridge, UK {nl347,nhc30}@cam.ac.uk Abstract Automatically recognising medical con- cepts mentioned in social media messages (e.g. tweets) enables several applications for enhancing health quality of people in a community, e.g. real-time monitoring of infectious diseases in population. How- ever, the discrepancy between the type of language used in social media and med- ical ontologies poses a major challenge. Existing studies deal with this challenge by employing techniques, such as lexi- cal term matching and statistical machine translation. In this work, we handle the medical concept normalisation at the se- mantic level. We investigate the use of neural networks to learn the transition be- tween layman’s language used in social media messages and formal medical lan- guage used in the descriptions of medi- cal concepts in a standard ontology. We evaluate our approaches using three differ- ent datasets, where social media texts are extracted from Twitter messages and blog posts. Our experimental results show that our proposed approaches significantly and consistently outperform existing effective baselines, which achieved state-of-the-art performance on several medical concept normalisation tasks, by up to 44%. 1 Introduction Existing studies (O’Connor et al., 2014; Lim- sopatham and Collier, 2015a; Limsopatham and Collier, 2015b) have shown that data from social media (e.g. Twitter1 and Facebook2) can be lever- aged to improve the understanding of patients’ ex- 1http://twitter.com 2http://facebook.com perience in healthcare, such as the spread of infec- tious diseases and side-effects of drugs. However, the lexical and grammatical variability of the lan- guage used in social media poses a key challenge for extracting information (Baldwin et al., 2013; O’Connor et al., 2014). In particular, the frequent use of informal language, non-standard grammar and abbreviation forms, as well as typos in social media messages has to be taken into account by effective information extraction systems. The task of medical concept normalisation for social media text, which aims to map a variable length social media message to a medical con- cept in some external coding system, is faced with a similar challenge (Limsopatham and Col- lier, 2015b). Traditional approaches, e.g. (Ris- tad and Yianilos, 1998; Aronson, 2001; Lu et al., 2011; McCallum et al., 2012), used prox- imity matching or heuristic string matching rules based on dictionary lookup when mapping texts to medical concepts. For example, Ristad and Yianilos (1998) incorporated edit-distance when mapping similar texts. The MetaMap system of Aronson (2001) applied a rule-based approach us- ing pre-defined variants of terms when mapping texts to medical concepts in the UMLS Metathe- saurus3. However, as shown in Table 1, exist- ing string matching techniques may not be able to map the social media message “moon face and 30 lbs in 6 weeks” to the medical concept ‘Weight Gain’, or map …

Content truncated to 500 words