Abstract:
Using the current state of the art in life science publication search (e.g., PubMed), one can efficiently search for resources containing particular key-words or their combinations. It is impossible to search for abstract concepts and expressive relations between them (e.g., type of, different from or part of), though. Nevertheless, such a more expressive¿semantic¿search could largely reduce the efforts related to finding appropriate answers in biomedical articles. In this paper we identify challenges related to building a semantic publication search engine. Then we describe the architecture and usage principles of a tool tackling them. Eventually, we report on the tool¿s deployment on oncological literature data and preliminary tests with domain experts.
