{"_buckets": {"deposit": "c0c14dcf-6945-49da-83df-8fd7f0b9f6bd"}, "_deposit": {"created_by": 3, "id": "3188", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "3188"}, "status": "published"}, "_oai": {"id": "oai:repository.ninjal.ac.jp:00003188", "sets": ["482"]}, "author_link": ["4607", "10719", "10720"], "item_10003_biblio_info_32": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2020", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "330", "bibliographicPageStart": "324", "bibliographicVolumeNumber": "5", "bibliographic_titles": [{"bibliographic_title": "言語資源活用ワークショップ発表論文集"}, {"bibliographic_title": "Proceedings of Language Resources Workshop", "bibliographic_titleLang": "en"}]}]}, "item_10003_description_27": {"attribute_name": "会議概要（会議名, 開催地, 会期, 主催者等）", "attribute_value_mlt": [{"subitem_description": "会議名: 言語資源活用ワークショップ2020, 開催地: オンライン, 会期: 2020年9月8日−9日, 主催: 国立国語研究所 コーパス開発センター", "subitem_description_type": "Other"}]}, "item_10003_description_29": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "『日本語日常会話コーパス』(CEJC)の短単位情報付与作業では、以下のような作業工程を踏んでいる：(i) 転記をMeCab（解析器）+ UniDic（解析辞書）で自動解析、(ii) 音声を聴取しながら、付加情報の一つである「発音形」のみを人手修正、(iii) 人手修正された発音形を尊重しつつ再び自動解析、(iv) 短単位情報（境界情報、発音形以外の付加情報）を人手修正。この作業工程の妥当性を検証するため、人手修正済みデータを対象に、複数の版の現代話し言葉UniDic（Ver2.2.0, 2.3.0, 3.0.1）で自動解析をしなおし、出力を比較した。その結果、どの版のUniDicを使っても、人手修正された発音形の情報を用いる方が、そうでない場合に比べ、短単位情報の精度向上を見込めることがわかった。特に、古い版のUniDic (Ver2.2.0)ではそれが顕著であった（境界＋品詞＋語彙素（F値）：0.944→0.962）。一方で、最新版のUniDic (Ver3.0.1)では効果は限定的である（同：0.976→0.979）。", "subitem_description_type": "Abstract"}]}, "item_10003_description_43": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_10003_description_51": {"attribute_name": "著者所属", "attribute_value_mlt": [{"subitem_description": "国立国語研究所", "subitem_description_type": "Other"}, {"subitem_description": "国立国語研究所", "subitem_description_type": "Other"}]}, "item_10003_description_52": {"attribute_name": "著者所属(英)", "attribute_value_mlt": [{"subitem_description": "National Institute for Japanese Language and Linguistics", "subitem_description_type": "Other"}, {"subitem_description": "National Institute for Japanese Language and Linguistics", "subitem_description_type": "Other"}]}, "item_10003_identifier_registration": {"attribute_name": "ID登録", "attribute_value_mlt": [{"subitem_identifier_reg_text": "10.15084/00003172", "subitem_identifier_reg_type": "JaLC"}]}, "item_10003_publisher_45": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "国立国語研究所"}]}, "item_10003_relation_40": {"attribute_name": "関連サイト", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "言語資源活用ワークショップ2020"}], "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://pj.ninjal.ac.jp/corpus_center/lrw2020.html", "subitem_relation_type_select": "URI"}}]}, "item_10003_version_type_44": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "西川, 賢哉"}, {"creatorName": "ニシカワ, ケンヤ", "creatorNameLang": "ja-Kana"}, {"creatorName": "Nishikawa, Ken\u0027ya", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "4607", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "50780516", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000050780516"}, {"nameIdentifier": "kennskw", "nameIdentifierScheme": "researchmap", "nameIdentifierURI": "https://researchmap.jp/kennskw"}]}, {"creatorNames": [{"creatorName": "渡邊, 友香"}, {"creatorName": "ワタナベ, ユカ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "10719", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Watanabe, Yuka", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "10720", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2021-03-04"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "LRW2020_33_P-4-6.pdf", "filesize": [{"value": "641.2 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 641200.0, "url": {"label": "LRW2020_33_P-4-6.pdf", "url": "https://repository.ninjal.ac.jp/record/3188/files/LRW2020_33_P-4-6.pdf"}, "version_id": "5f6fed42-789a-4ad7-b2dd-81a2afbf6f8d"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "日本語日常会話コーパス(CEJC)", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Corpus of Everyday Japanese Conversation (CEJC)", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "『日本語日常会話コーパス』に対する短単位情報付与：作業工程と評価", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "『日本語日常会話コーパス』に対する短単位情報付与：作業工程と評価"}, {"subitem_title": "Short Unit Word Annotation for the Corpus of Everyday Japanese Conversation : Procedures and Evaluation", "subitem_title_language": "en"}]}, "item_type_id": "10003", "owner": "3", "path": ["482"], "permalink_uri": "https://doi.org/10.15084/00003172", "pubdate": {"attribute_name": "公開日", "attribute_value": "2021-03-05"}, "publish_date": "2021-03-05", "publish_status": "0", "recid": "3188", "relation": {}, "relation_version_is_last": true, "title": ["『日本語日常会話コーパス』に対する短単位情報付与：作業工程と評価"], "weko_shared_id": 3}