Entry Sharma:2008:AMI 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{Sharma:2008:AMI,
  author =       "Utpal Sharma and Jugal K. Kalita and Rajib K. Das",
  title =        "Acquisition of Morphology of an {Indic} Language from
                 Text Corpus",
  journal =      j-TALIP,
  volume =       "7",
  number =       "3",
  pages =        "9:1--9:??",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "https://doi.org/10.1145/1386869.1386871",
  ISSN =         "1530-0226 (print), 1558-3430 (electronic)",
  ISSN-L =       "1530-0226",
  bibdate =      "Fri Aug 22 13:11:51 MDT 2008",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/talip.bib",
  abstract =     "This article describes an approach to unsupervised
                 learning of morphology from an unannotated corpus for a
                 highly inflectional Indo-European language called
                 Assamese spoken by about 30 million people. Although
                 Assamese is one of India's national languages, it
                 utterly lacks computational linguistic resources. There
                 exists no prior computational work on this language
                 spoken widely in northeast India. The work presented is
                 pioneering in this respect. In this article, we discuss
                 salient issues in Assamese morphology where the
                 presence of a large number of suffixal determiners,
                 sandhi, samas, and the propensity to use suffix
                 sequences make approximately 50\% of the words used in
                 written and spoken text inflected. We implement methods
                 proposed by Gaussier and Goldsmith on acquisition of
                 morphological knowledge, and obtain F-measure
                 performance below 60\%. This motivates us to present a
                 method more suitable for handling suffix sequences,
                 enabling us to increase the F-measure performance of
                 morphology acquisition to almost 70\%. We describe how
                 we build a morphological dictionary for Assamese from
                 the text corpus. Using the morphological knowledge
                 acquired and the morphological dictionary, we are able
                 to process small chunks of data at a time as well as a
                 large corpus. We achieve approximately 85\% precision
                 and recall during the analysis of small chunks of
                 coherent text.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Asian Language Information
                 Processing",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J820",
  keywords =     "Assamese; Indo-European languages; machine learning;
                 morphology",
}

Related entries