@inproceedings{sinkkila-et-al-subject-indexing-2011,
  OPTkey = 	 {},
  author = 	 {Reetta Sinkkilä and Osma Suominen and Eero Hyvönen},
  title = 	 {Automatic Semantic Subject Indexing of Web Documents in Highly Inflected Languages},
  booktitle = {Proceedings of the 8th Extended Semantic Web Conference (ESWC 2011)},
  publisher = {Springer-Verlag},
  pages = {215--229},
  OPThowpublished = {},
  month = 	 {June},
  year = 	 {2011},
  location = {Heraklion, Greece},
  abstract = {Structured semantic metadata about unstructured web documents can be created
using automatic subject indexing methods, avoiding laborious manual
indexing. A succesful automatic subject indexing tool for the web should
work with texts in multiple languages and be independent of the domain of
discourse of the documents and controlled vocabularies. However, analyzing
text written in a highly inflected language requires word form normalization
that goes beyond rule-based stemming algorithms. We have tested the
state-of-the art automatic indexing tool Maui on Finnish texts using three
stemming and lemmatization algorithms and tested it with documents and
vocabularies of different domains. Both of the lemmatization algorithms we
tested performed significantly better than a rule-based stemmer, and the
subject indexing quality was found to be comparable to that of human
indexers.},
  OPTannote = 	 {},
  OPTproject = {http://www.seco.tkk.fi/projects/finnonto/finnonto2/,http://www.seco.tkk.fi/services/arpa/}
}