Does Term Expansion Matter for the Retrieval of Biodiversity Data?

While term expansion techniques are well investigated for many domains, semantic enrichment of keyword queries for the retrieval of scientific datasets is still paid little attention to. In particular, a systematic analysis of which kind of semantically related concepts lead to the most relevant results is missing. Based on query expansion techniques, we semantically enriched search queries provided by biodiversity researchers to answer specific research questions. We applied them to a system indexing over 92,856 biological metadata files harvested from GFBio – the German Federation for Biological Data. We compared the outcome with the original keyword-based query. The result reveals that enriched keywords deliver a larger number of relevant datasets and that datasets retrieved based on keywords and their synonyms were judged more relevant. Query expansion with other related concepts returned a mixed picture.

http://ceur-ws.org/Vol-1695/paper2.pdf

supplementary material

@Conference{LoefflerKlan2016,
  author =    {L\"offler, Felicitas and Klan, Friederike},
  title =     {Does Term Expansion Matter for the Retrieval of Biodiversity Data?},
  booktitle = {Joint Proceedings of the Posters and Demos Track of the 12th International Conference on Semantic Systems - SEMANTiCS2016 and the 1st International Workshop on Semantic Change \& Evolving Semantics (SuCCESS'16), co-located with the 12th International Conference on Semantic Systems (SEMANTiCS 2016)},
  year =      {2016},
  editor =    {Martin, Michael and Cuquet, Martí and Folmer, Erwin},
  publisher = {CEUR Workshop Proceedings},
  url =       {http://ceur-ws.org/Vol-1695/paper2.pdf}
}