UD_GU_BioTM at TREC 2017: Precision Medicine Track

This paper describes the system developed for the TREC 2017 PM track. We employed a two-part system to generate the ranked list of clinical trials and scientific abstracts. The first part pertains to query expansion and document retrieval from document index. The second part pertains to generating the final ranked list by implementing a heuristic scoring method. The scoring for clinical trials involved grouping trials based on different trial fields and extraction of features based on occurrences of gene/disease and other terms in the trial. The scoring for scientific abstracts involved applying a NLP system to extract relations from text, as well as extraction of additional information relevant to precision medicine. Keywords—TREC 2017, precision medicine, NLP