@inproceedings{PasternackRo09,
 author= {J. Pasternack and D. Roth},
 title= {Extracting Article Text from the Web with Maximum Subsequence Segmentation},
 booktitle= {The International World Wide Web Conference},
 month= {April},
 pages= {},
 year= {2009},
 comment= {A new global optimization technique,
 maximum subsequence,
 is used to accurately identify and extract article text from HTML documents in linear time},
 projects = {IE} URL = "http://l2r.cs.uiuc.edu/~danr/Papers/PasternackRo09.pdf",
 }