Subword Retrieval on Biomedical Documents

Document retrieval in languages with a rich and com- plex morphology - particularly in terms of derivation and (single-word) composition - suffers from serious perfor- mance degradation with the stemming-only query-term-to- text-word matching paradigm. We propose an alternative ap- proach in which morphologically complex word forms are segmented into relevant subwords (such as stems, prefixes, suffixes), and subwords constitute the basic unit for index- ing and retrieval. We evaluate our approach on a biomedical document collection.