Entry Fukumoto:2007:TTB from talip.bib

Last update: Sun Oct 15 02:55:04 MDT 2017                Valid HTML 3.2!

Index sections

Top | Symbols | Numbers | Math | A | B | C | D | E | F | G | H | I | J | K | L | M | N | O | P | Q | R | S | T | U | V | W | X | Y | Z

BibTeX entry

@Article{Fukumoto:2007:TTB,
  author =       "Fumiyo Fukumoto and Yoshimi Suzuki",
  title =        "Topic tracking based on bilingual comparable corpora
                 and semisupervised clustering",
  journal =      j-TALIP,
  volume =       "6",
  number =       "3",
  pages =        "11:1--11:??",
  month =        nov,
  year =         "2007",
  CODEN =        "????",
  DOI =          "https://doi.org/10.1145/1290002.1290005",
  ISSN =         "1530-0226 (print), 1558-3430 (electronic)",
  ISSN-L =       "1530-0226",
  bibdate =      "Mon Jun 16 17:11:45 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/talip.bib",
  abstract =     "In this paper, we address the problem of skewed data
                 in topic tracking: the small number of stories labeled
                 positive as compared to negative stories and propose a
                 method for estimating effective training stories for
                 the topic-tracking task. For a small number of labeled
                 positive stories, we use bilingual comparable, i.e.,
                 English, and Japanese corpora, together with the EDR
                 bilingual dictionary, and extract story pairs
                 consisting of positive and associated stories. To
                 overcome the problem of a large number of labeled
                 negative stories, we classified them into clusters.
                 This is done using a semisupervised clustering
                 algorithm, combining $k$ means with EM. The method was
                 tested on the TDT English corpus and the results showed
                 that the system works well when the topic under
                 tracking is talking about an event originating in the
                 source language country, even for a small number of
                 initial positive training stories.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Asian Language Information
                 Processing",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J820",
  keywords =     "bilingual comparable corpora; clustering; EM
                 algorithm; N-gram model; topic detection and tracking",
}

Related entries