<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-03-07T06:47:09Z</responseDate>
  <request metadataPrefix="oai_dc" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00049159">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00049159</identifier>
        <datestamp>2025-01-19T23:36:24Z</datestamp>
        <setSpec>1164:4179:4271:4273</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns="http://www.w3.org/2001/XMLSchema" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>連語パターンによる日－韓機械翻訳システムの構築とその評価</dc:title>
          <dc:title>Collocation - Based MT system from Japanese to Korean and Its Evaluation</dc:title>
          <dc:creator>朴, 哲済</dc:creator>
          <dc:creator>文, 敬姫</dc:creator>
          <dc:creator>郭, 鍾根</dc:creator>
          <dc:creator>李, 鐘赫</dc:creator>
          <dc:creator>李, 根培</dc:creator>
          <dc:creator>Chul-Jae, Park</dc:creator>
          <dc:creator>Kyong-Hee, Moon</dc:creator>
          <dc:creator>Jong-Geun, Kwak</dc:creator>
          <dc:creator>Jong-Hyeok, Lee</dc:creator>
          <dc:creator>Geunbae, Lee</dc:creator>
          <dc:description>本稿では，連語パターンによる日?韓機械翻訳システムの実現と評価について述べる．筆者らは，日本語での連語パターンを作成し，変換規則として用いることにより多義語の問題を解決した．述部の生成は様相類意味素テーブルを利用した．日本語解析ではCYK法を改良し，辞書検索回数を少なくした．我々は，このような機械翻訳システムを鉄鋼関係の特許文書翻訳のために構築し，その性能を評価法によって分析した．その結果，翻訳成功率は93％であるし，長文対応力，翻訳処理速度，解析生成能力において十分有効であることを確認した．</dc:description>
          <dc:description>In this paper, we present a collocation-based transfer model in which a source word with multiple meaning may have a set of transfer rules for word-sense disambiguation. To effectively encode the ordering information of modalities and their surface morphemes, we constructed a Modality-Feature-Ordering and Lexicalizing Table called MFOLT. The Japanese morphological analyzer is based on the CYK algorithm which access dictionary less than others. By implementing the above concepts, we constructed a Japanese-Korean machine translation system for iron and steel patent text, and obtained about 93% of accuracy transfer rate. From this experimental result, the system showed great effectiveness.</dc:description>
          <dc:description>technical report</dc:description>
          <dc:publisher>情報処理学会</dc:publisher>
          <dc:date>1995-09-14</dc:date>
          <dc:format>application/pdf</dc:format>
          <dc:identifier>情報処理学会研究報告自然言語処理（NL）</dc:identifier>
          <dc:identifier>89(1995-NL-109)</dc:identifier>
          <dc:identifier>1995</dc:identifier>
          <dc:identifier>9</dc:identifier>
          <dc:identifier>18</dc:identifier>
          <dc:identifier>AN10115061</dc:identifier>
          <dc:identifier>https://ipsj.ixsq.nii.ac.jp/record/49159/files/IPSJ-NL95109002.pdf</dc:identifier>
          <dc:language>jpn</dc:language>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
