@inproceedings{milne2008effective,
  abstract = {This paper describes a new technique for obtaining measures of semantic relatedness. Like other recent approaches, it uses Wikipedia to provide structured world knowledge about the terms of interest. Out approach is unique in that it does so using the hyperlink structure of Wikipedia rather than its category hierarchy or textual content. Evaluation with manually defined measures of semantic relatedness reveals this to be an effective compromise between the ease of computation of the former approach and the accuracy of the latter.},
  author = {Milne, David and Witten, Ian H.},
  booktitle = {Proceeding of AAAI Workshop on Wikipedia and Artificial Intelligence: an Evolving Synergy},
  interhash = {f8b0b3ba8f4a1c20e3d5d732a221f102},
  intrahash = {f4daaa2541e89bdd1996c42f8f4b3a4b},
  month = jul,
  pages = {25--30},
  publisher = {AAAI Press},
  title = {An effective, low-cost measure of semantic relatedness obtained from Wikipedia links},
  url = {https://www.aaai.org/Papers/Workshops/2008/WS-08-15/WS08-15-005.pdf},
  year = 2008
}

@inproceedings{milne2008learning,
  abstract = {This paper describes how to automatically cross-reference documents with Wikipedia: the largest knowledge base ever known. It explains how machine learning can be used to identify significant terms within unstructured text, and enrich it with links to the appropriate Wikipedia articles. The resulting link detector and disambiguator performs very well, with recall and precision of almost 75%. This performance is constant whether the system is evaluated on Wikipedia articles or "real world" documents.</p> <p>This work has implications far beyond enriching documents with explanatory links. It can provide structured knowledge about any unstructured fragment of text. Any task that is currently addressed with bags of words - indexing, clustering, retrieval, and summarization to name a few - could use the techniques described here to draw on a vast network of concepts and semantics.},
  address = {New York, NY, USA},
  author = {Milne, David and Witten, Ian H.},
  booktitle = {Proceedings of the 17th ACM conference on Information and knowledge management},
  doi = {10.1145/1458082.1458150},
  interhash = {44159e289485110212602792e72bbd74},
  intrahash = {fd9cd6bbf302731d5af3f6e748cdb359},
  isbn = {978-1-59593-991-3},
  location = {Napa Valley, California, USA},
  pages = {509--518},
  publisher = {ACM},
  title = {Learning to link with wikipedia},
  url = {http://doi.acm.org/10.1145/1458082.1458150},
  year = 2008
}

@inproceedings{ting:ijcai97,
  author = {Ting, Kai Ming and Witten, Ian H.},
  booktitle = {in Procs. International Joint Conference on Artificial Intelligence},
  interhash = {f1f7082296d57fcef07b8156772bc884},
  intrahash = {45579016ebfe71170fe57938e0c3002d},
  pages = {866--871},
  publisher = {Morgan Kaufmann},
  title = {Stacked generalization: when does it work},
  year = 1997
}

@inproceedings{conf/pakdd/HuangMFW09,
  author = {Huang, Anna and Milne, David N. and Frank, Eibe and Witten, Ian H.},
  booktitle = {PAKDD},
  crossref = {conf/pakdd/2009},
  date = {2009-04-25},
  editor = {Theeramunkong, Thanaruk and Kijsirikul, Boonserm and Cercone, Nick and Ho, Tu Bao},
  ee = {http://dx.doi.org/10.1007/978-3-642-01307-2_62},
  interhash = {b2ea40479e6537693a659a4342892fee},
  intrahash = {63d65d3bd978e39f33f39222be9a3f76},
  isbn = {978-3-642-01306-5},
  pages = {628-636},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {Clustering Documents Using a Wikipedia-Based Concept Representation.},
  url = {http://dblp.uni-trier.de/db/conf/pakdd/pakdd2009.html#HuangMFW09},
  volume = 5476,
  year = 2009
}

@book{books/mk/WittenMB99,
  author = {Witten, Ian H. and Moffat, Alistair and Bell, Timothy C.},
  interhash = {e27de62d31e9665025dc788cb30027d5},
  intrahash = {99a44801fa131f7fda77e769791f5f78},
  isbn = {1-55860-570-3},
  publisher = {Morgan Kaufmann},
  title = {Managing Gigabytes: Compressing and Indexing Documents and Images, Second Edition},
  url = {http://www.cs.mu.oz.au/mg/},
  year = 1999
}

@misc{Medelyan2008,
  abstract = {  Wikipedia is a goldmine of information; not just for its many readers, but
also for the growing community of researchers who recognize it as a resource of
exceptional scale and utility. It represents a vast investment of manual effort
and judgment: a huge, constantly evolving tapestry of concepts and relations
that is being applied to a host of tasks.
  This article provides a comprehensive description of this work. It focuses on
research that extracts and makes use of the concepts, relations, facts and
descriptions found in Wikipedia, and organizes the work into four broad
categories: applying Wikipedia to natural language processing; using it to
facilitate information retrieval and information extraction; and as a resource
for ontology building. The article addresses how Wikipedia is being used as is,
how it is being improved and adapted, and how it is being combined with other
structures to create entirely new resources. We identify the research groups
and individuals involved, and how their work has developed in the last few
years. We provide a comprehensive list of the open-source software they have
produced. We also discuss the implications of this work for the long-awaited
semantic web.
},
  author = {Medelyan, Olena and Legg, Catherine and Milne, David and Witten, Ian H.},
  interhash = {6614c7cd27d80abd691b2ef463941d1c},
  intrahash = {0e7499a4f087f74ad0be674047cf315d},
  note = {cite arxiv:0809.4530
Comment: An extensive survey of re-using information in Wikipedia in natural
  language processing, information retreival and extraction and ontology
  building. submitted},
  title = {Mining Meaning from Wikipedia},
  url = {http://arxiv.org/abs/0809.4530},
  year = 2008
}

@book{books/mk/WittenMB99,
  author = {Witten, Ian H. and Moffat, Alistair and Bell, Timothy C.},
  interhash = {e27de62d31e9665025dc788cb30027d5},
  intrahash = {99a44801fa131f7fda77e769791f5f78},
  isbn = {1-55860-570-3},
  publisher = {Morgan Kaufmann},
  title = {Managing Gigabytes: Compressing and Indexing Documents and Images, Second Edition},
  url = {http://www.cs.mu.oz.au/mg/},
  year = 1999
}

@book{citeulike:340715,
  author = {Witten, Ian H. and Frank, Eibe},
  citeulike-article-id = {340715},
  edition = {Second},
  howpublished = {Paperback},
  interhash = {6d7648942e58f322a39a1e8c37edfec6},
  intrahash = {57ade2d873735d4c54d44365dafa7605},
  isbn = {0120884070},
  month = {June},
  priority = {0},
  publisher = {Morgan Kaufmann},
  series = {Morgan Kaufmann Series in Data Management Sys},
  title = {Data Mining: Practical Machine Learning Tools and Techniques},
  url = {http://www.amazon.fr/exec/obidos/ASIN/0120884070/citeulike04-21},
  year = 2005
}