@inproceedings{Grover:2000,
  abstract = {We describe LT TTT, a recently developed software system which provides tools to perform text tokenisation and mark-up. The system includes ready-made components to segment text into paragraphs, sentences, words and other kinds of token but, crucially, it also allows users to tailor rule-sets to produce mark-up appropriate for particular applications. We present three case studies of our use of LT TTT: named-entity recognition (MUC-7), citation recognition and mark-up and the preparation of a corpus in the medical domain. We conclude with a discussion of the use of browsers to visualise marked-up text.},
  added-at = {2007-12-14T02:39:43.000+0100},
  author = {Grover, Claire and Matheson, Colin and Mikheev, Andrei and Moens, Marc},
  biburl = {http://www.bibsonomy.org/bibtex/225d5028cf05ec729bf39533078381177/diego_ma},
  booktitle = {Proc. LREC 2000},
  interhash = {d0e9898b2a17acf0de47e438317368ef},
  intrahash = {25d5028cf05ec729bf39533078381177},
  keywords = {tokeniser XML},
  timestamp = {2007-12-14T02:39:43.000+0100},
  title = {{LT TTT} --- A Flexible Tokenisation Tool},
  url = {http://www.ltg.ed.ac.uk/papers/},
  year = 2000
}