Exploring Abbreviation Expansion for Genomic Information Retrieval

Abbreviations are commonly found instances of synonymy in Biomedical journal papers. Information retrieval systems that index paragraphs rather than full-text articles are more susceptible to term variation of this kind, since abbreviations are typically only defined once at the beginning of the text. One solution to this problem is to expand the user query automatically with all possible abbreviation instances for each query term. In this paper, we compare the effectiveness of two abbreviation expansion techniques on the TREC 2006 Genomics Track queries and collection. Our results show that for highly ambiguous abbreviations the query collocation effect isn’t strong enough to deter the retrieval of erroneous passages. We conclude that full-text abbreviation resolution prior to passage indexing is the most appropriate approach to this problem.