{
  "eprintid": "156",
  "rev_number": "5",
  "eprint_status": "archive",
  "dir": "disk0/00/00/01/56",
  "datestamp": "2009-04-06 19:13:27",
  "lastmod": "2009-04-14 04:37:12",
  "status_changed": "2009-04-06 19:13:27",
  "type": "conference_item",
  "metadata_visibility": "show",
  "item_issues_count": "0",
  "creators": {
    "item": {
      "name": {
        "family": "Sato",
        "given": "Satoshi"
      },
      "id": "",
      "country": "",
      "affiliation": "Nagoya University"
    }
  },
  "track": "Poster Session",
  "title": "Crawling English-Japanese Person-Name Transliterations from the Web",
  "ispublished": "pub",
  "full_text_status": "public",
  "pres_type": "poster",
  "abstract": "Automatic compilation of lexicon is a dream of lexicon compilers as well as lexicon users. This paper proposes a system that crawls English-Japanese person-name transliterations from the Web, which works a back-end collector for automatic compilation of bilingual person-name lexicon. Our crawler collected 561K transliterations in five months. From them, an English-Japanese person-name lexicon with 406K entries has been compiled by an automatic post processing. This lexicon is much larger than other similar resources including English-Japanese lexicon of HeiNER obtained from Wikipedia. names written in Latin script are transliterated into one in Katakana script according to their pronunciations. English-Japanese transliteration of person name is difficult because of several reasons, such as limited coverage of existing bilingual lexicons, non-English (e.g., French and German) person names appeared in English texts, and spelling variants in Katakana script. 2. There is a possibility that we can compile a large EnglishJapanese person-name lexicon from the Web, because a lot of transliteration instances of person names exist on the Web. Actually, human translators use the Web as a virtual low-quality bilingual lexicon. 3. New person names are produced; new person-name transliterations are produced in every day. Human translators hope frequent update of bilingual personname lexicon. This paper proposes a system that crawls English-Japanese person-name transliterations from the Web, which works as a back-end collector for automatic lexicon compilation. From collected transliterations, a bilingual person-name lexicon is produced by an automatic post processing. This attempt of automatic lexicon compilation can be viewed as a conversion from a virtual low-quality bilingual lexicon (i.e., the Web) to a real high-quality bilingual lexicon.",
  "date": "2009-04",
  "pagerange": "1151-1151",
  "event_title": "18th International World Wide Web Conference",
  "event_location": "Madrid, Spain",
  "event_dates": "April 20th-24th, 2009",
  "event_type": "conference",
  "refereed": "TRUE",
  "documents": {
    "document": {
      "docid": "156",
      "rev_number": "4",
      "eprintid": "156",
      "pos": "1",
      "format": "application/pdf",
      "language": "en",
      "security": "public",
      "main": "p1151.pdf",
      "content": "published",
      "files": {
        "file": {
          "filename": "p1151.pdf",
          "filesize": "595016",
          "url": "http://www2009.eprints.org/156/1/p1151.pdf"
        }
      }
    }
  }
}