<?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>2026-05-13T06:53:50Z</responseDate>
  <request metadataPrefix="jpcoar_1.0" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00212201">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00212201</identifier>
        <datestamp>2025-01-19T17:34:40Z</datestamp>
        <setSpec>1164:4179:10535:10649</setSpec>
      </header>
      <metadata>
        <jpcoar:jpcoar xmlns:datacite="https://schema.datacite.org/meta/kernel-4/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcndl="http://ndl.go.jp/dcndl/terms/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:jpcoar="https://github.com/JPCOAR/schema/blob/master/1.0/" xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rioxxterms="http://www.rioxx.net/schema/v2.0/rioxxterms/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="https://github.com/JPCOAR/schema/blob/master/1.0/" xsi:schemaLocation="https://github.com/JPCOAR/schema/blob/master/1.0/jpcoar_scm.xsd">
          <dc:title>深層学習による文書の話題分類の判断根拠の提示に関する一考察</dc:title>
          <dc:title xml:lang="en">A Study on Presenting Decision Rationale for Topic Classification of Documents by Deep Learning</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>為栗, 敦生</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>中村, 鴻介</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>高橋, 良颯</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>山口, 実靖</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Atsuki, Tamekuri</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Kosuke, Nakamura</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Yoshihaya, Takahashi</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Saneyasu, Yamaguchi</jpcoar:creatorName>
          </jpcoar:creator>
          <datacite:description descriptionType="Other">深層学習は文書分類等の自然言語処理にて活用され，Self-Attention などが大きな成果をあげている．一方で深層学習による分類は，分類精度は高いがその判断根拠を人間が理解することが困難であるとの指摘がされている．本稿では，テーマが定められたニュース記事群のテーマによる分類のタスクに着目し，深層学習による分類の判断根拠の提示手法について考察する．具体的には，LSTM Attention により記事分類を行い，高い精度で分類をできることを示す．そして，Attention 値や既存の判断根拠提示手法 Smooth-grad に着目し，自然言語記事分類の判断根拠提示手法について考察する．また性能評価により，これらに着目することにより判断根拠を提示できることを示す．</datacite:description>
          <datacite:description descriptionType="Other">Deep learning has been used in natural language processing (NLP) such as document classification. In particular, Self-Attention has achieved significant results in NLP. However, it has been pointed out that although deep learning highly accurately classifies documents, it is difficult to interpret the basis of the decision. In this paper, we focus on the task of classifying news documents by their theme. We then propose methods for presenting the interpretability for classification decisions by deep learning. We first classify documents with LSTM Attention and show that this can classify documents with high accuracy. We second propose five methods for providing the basis of the decision by focusing on various values, e.g. Attention. Finally, we evaluate the methods and show that these methods can present interpretability.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2021-07-20</datacite:date>
          <dc:language>jpn</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_18gh">technical report</dc:type>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/212201</jpcoar:identifier>
          <jpcoar:sourceIdentifier identifierType="ISSN">2188-8779</jpcoar:sourceIdentifier>
          <jpcoar:sourceIdentifier identifierType="NCID">AN10115061</jpcoar:sourceIdentifier>
          <jpcoar:sourceTitle>研究報告自然言語処理（NL）</jpcoar:sourceTitle>
          <jpcoar:volume>2021-NL-249</jpcoar:volume>
          <jpcoar:issue>1</jpcoar:issue>
          <jpcoar:pageStart>1</jpcoar:pageStart>
          <jpcoar:pageEnd>7</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="IPSJ-NL21249001.pdf">https://ipsj.ixsq.nii.ac.jp/record/212201/files/IPSJ-NL21249001.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>1.2 MB</jpcoar:extent>
            <datacite:date dateType="Available">2023-07-20</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
