Entry Tepper:2010:IMU 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{Tepper:2010:IMU,
  author =       "Michael Tepper and Fei Xia",
  title =        "Inducing Morphemes Using Light Knowledge",
  journal =      j-TALIP,
  volume =       "9",
  number =       "1",
  pages =        "3:1--3:??",
  month =        mar,
  year =         "2010",
  CODEN =        "????",
  DOI =          "https://doi.org/10.1145/1731035.1731038",
  ISSN =         "1530-0226 (print), 1558-3430 (electronic)",
  ISSN-L =       "1530-0226",
  bibdate =      "Mon Mar 29 15:34:01 MDT 2010",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/talip.bib",
  abstract =     "Allomorphic variation, or form variation among morphs
                 with the same meaning, is a stumbling block to
                 morphological induction (MI). To address this problem,
                 we present a hybrid approach that uses a small amount
                 of linguistic knowledge in the form of orthographic
                 rewrite rules to help refine an existing MI-produced
                 segmentation. Using rules, we derive underlying
                 analyses of morphs---generalized with respect to
                 contextual spelling differences---from an existing
                 surface morph segmentation, and from these we learn a
                 morpheme-level segmentation. To learn morphemes, we
                 have extended the Morfessor segmentation algorithm
                 [Creutz and Lagus 2004; 2005; 2006] by using rules to
                 infer possible underlying analyses from surface
                 segmentations. A segmentation produced by Morfessor
                 Categories-MAP Software v. 0.9.2 is used as input to
                 our procedure and as a baseline that we evaluate
                 against. To suggest analyses for our procedure, a set
                 of language-specific orthographic rules is needed. Our
                 procedure has yielded promising improvements for
                 English and Turkish over the baseline approach when
                 tested on the Morpho Challenge 2005 and 2007 style
                 evaluations. On the Morpho Challenge 2007 test
                 evaluation, we report gains over the current best
                 unsupervised contestant for Turkish, where our
                 technique shows a 2.5\% absolute {\em F\/} -score
                 improvement.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Asian Language Information
                 Processing",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J820",
  keywords =     "allomorphy; computational linguistics; machine
                 learning; Morphological induction",
}

Related entries