Dissemination of medical information using mobile phones is still in a nascent stage because of their limited features-lack of penetration of mobile internet, small screen size etc. We present the design of a drug QA system that could be used for providing information about medicines over short message service (SMS). We begin with a survey of the drug information domain and classify the drug related queries into a set of predefined classes. Our system cleansing of millions of data records. He co-founded the AND (Analytics for Noisy Unstructured Text Data) workshop series and also co-chaired the first four workshops, 2007-2010. He was guest co-editor of two special issues on Noisy Text Analytics in the International Journal of Document Analysis and Recognition in 2007 and 2009. Parikshit Sondhi received an Integrated Dual Degree (BS + MS) in Computer Science from Indian Institute of Technology Roorkee, India, in 2008. He is currently a Computer Science PhD candidate at the University of Illinois Urbana Champaign. His research interests include information retrieval and mining applications in the biomedical domain. This paper is a revised and expanded version of a paper entitled 'Mobile medicine: providing drug related information through natural language queries via SMS' presented at

Community based Question Answering archives have emerged as a very useful resource for instant access to comprehensive information in response to user queries. However, its access remains restricted to internet users. Access to this resource through Short Message Service (SMS) requires that a high precision automatic similar question matching system be built in order to decrease the search time by decreasing the number of SMS exchanges required. This paper proposes a solution that handles inherent noise in SMS queries through variant search, modeling the problem as one of combinatorial search. Following this, it uses syntactic tree matching to improve the ranking scheme. We present our analysis of the system and conduct experiments to test its feasibility. Experiments show that our approach outperforms the existing approaches significantly.

No abstract