User intent behind medical queries: an evaluation of entity mapping approaches with metamap and freebase

This work focuses on understanding the user intent in the<br> medical domain. The combination of Semantic Web and information<br> retrieval technologies promises a better comprehension<br> of user intents. Mapping queries to entities using<br> Freebase is not novel, but so far only one entity per query<br> could be identified. We overcome this limitation using annotations<br> provided by Metamap. Also, different approaches to<br> map queries to Freebase are explored and evaluated. We<br> propose an indirect evaluation of the mappings, through<br> user intent defined by classes such as Symptoms, Diseases or<br> Treatments. Our experiments show that by using the concepts<br> annotated by Metamap it is possible to improve the<br> accuracy and F1 performances of mappings from queries to<br> Freebase entities