Entry Lee:2006:ABN 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{Lee:2006:ABN,
  author =       "Chun-Jen Lee and Jason S. Chang and Jyh-Shing R.
                 Jang",
  title =        "Alignment of bilingual named entities in parallel
                 corpora using statistical models and multiple knowledge
                 sources",
  journal =      j-TALIP,
  volume =       "5",
  number =       "2",
  pages =        "121--145",
  month =        jun,
  year =         "2006",
  CODEN =        "????",
  DOI =          "https://doi.org/10.1145/1165255.1165257",
  ISSN =         "1530-0226 (print), 1558-3430 (electronic)",
  ISSN-L =       "1530-0226",
  bibdate =      "Thu Oct 5 07:00:29 MDT 2006",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/talip.bib",
  abstract =     "Named entity (NE) extraction is one of the fundamental
                 tasks in natural language processing (NLP). Although
                 many studies have focused on identifying NEs within
                 monolingual documents, aligning NEs in bilingual
                 documents has not been investigated extensively due to
                 the complexity of the task. In this article we
                 introduce a new approach to aligning bilingual NEs in
                 parallel corpora by incorporating statistical models
                 with multiple knowledge sources. In our approach, we
                 model the process of translating an English NE phrase
                 into a Chinese equivalent using lexical
                 translation\slash transliteration probabilities for
                 word translation and alignment probabilities for word
                 reordering. The method involves automatically learning
                 phrase alignment and acquiring word translations from a
                 bilingual phrase dictionary and parallel corpora, and
                 automatically discovering transliteration
                 transformations from a training set of
                 name-transliteration pairs. The method also involves
                 language-specific knowledge functions, including
                 handling abbreviations, recognizing Chinese personal
                 names, and expanding acronyms. At runtime, the proposed
                 models are applied to each source NE in a pair of
                 bilingual sentences to generate and evaluate the target
                 NE candidates; the source and target NEs are then
                 aligned based on the computed probabilities.
                 Experimental results demonstrate that the proposed
                 approach, which integrates statistical models with
                 extra knowledge sources, is highly feasible and offers
                 significant improvement in performance compared to our
                 previous work, as well as the traditional approach of
                 IBM Model 4.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Asian Language Information
                 Processing",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?&idx=J820",
}

Related entries