@inproceedings{garbin2005disambiguating,
  abstract = {This research is aimed at the problem of disambiguating toponyms (place names) in terms of a classification derived by merging information from two publicly available gazetteers. To establish the difficulty of the problem, we measured the degree of ambiguity, with respect to a gazetteer, for toponyms in news. We found that 67.82% of the toponyms found in a corpus that were ambiguous in a gazetteer lacked a local discriminator in the text. Given the scarcity of human-annotated data, our method used unsupervised machine learning to develop disambiguation rules. Toponyms were automatically tagged with information about them found in a gazetteer. A toponym that was ambiguous in the gazetteer was automatically disambiguated based on preference heuristics. This automatically tagged data was used to train a machine learner, which disambiguated toponyms in a human-annotated news corpus at 78.5% accuracy.},
  acmid = {1220621},
  address = {Stroudsburg, PA, USA},
  author = {Garbin, Eric and Mani, Inderjeet},
  booktitle = {Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing},
  doi = {10.3115/1220575.1220621},
  interhash = {566910cb6e9745ee70da19d2ccafaffa},
  intrahash = {de574cf3bff3a3748fcd9bd5a9a0f3d1},
  location = {Vancouver, British Columbia, Canada},
  numpages = {8},
  pages = {363--370},
  publisher = {Association for Computational Linguistics},
  title = {Disambiguating toponyms in news},
  url = {http://dx.doi.org/10.3115/1220575.1220621},
  year = 2005
}

@book{Man2001a,
  address = {Amsterdam/Philadelphia},
  author = {Mani, Inderjeet},
  interhash = {af9f39887357cd72ad547dfe4e6345ef},
  intrahash = {67eff892b9728c22b51b108deafb2d6b},
  key = {Man2001a},
  label = {Automatic Summarization},
  optnumber = {3},
  publisher = {John Benjamins Publishing Company},
  series = {Natural Language Processing},
  title = {Automatic Summarization},
  type = {Book},
  volume = 3,
  year = 2001
}

@inproceedings{mani2004automatcally,
  abstract = {The emergence of vast quantities of on-line information has raised the importance of methods for automatic cataloguing of information in a variety of domains, including electronic commerce and bioinformatics. Ontologies can play a critical role in such cataloguing. In this paper, we describe a system that automatically induces an ontology from any large on-line text collection in a specific domain. The ontology that is induced consists of domain concepts, related by kind-of and part-of links. To achieve domain-independence, we use a combination of relatively shallow methods along with any available repositories of applicable background knowledge. We describe our evaluation experiences using these methods, and provide examples of induced structures.},
  address = {Geneva},
  author = {Mani, Inderjeet and Samuel, Ken and Concepcion, Kris and Vogel, David},
  booktitle = {Proceedings of the 3rd International Workshop on Computational Terminology},
  dateadded = {2006-07-18},
  interhash = {9ec83ddb1f251792d05345daa8357bf8},
  intrahash = {dce5c6301943fe6c9648cf671ceb167e},
  lastdatemodified = {2006-07-18},
  lastname = {Mani},
  month = {August},
  own = {notown},
  pdf = {mani04-automatically.pdf},
  read = {notread},
  title = {Automatcally Inducing Ontologies from Corpora},
  url = {http://-new.biomath.jussieu.fr/~pz/computerm2004.html},
  year = 2004
}