{"_buckets": {"deposit": "49f2152b-46d2-497a-aaed-394dc7cbf87f"}, "_deposit": {"created_by": 3, "id": "1702", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "1702"}, "status": "published"}, "_oai": {"id": "oai:repository.ninjal.ac.jp:00001702", "sets": ["268"]}, "author_link": ["4567"], "item_10003_biblio_info_32": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2018", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "530", "bibliographicPageStart": "519", "bibliographicVolumeNumber": "3", "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2018, 開催地: 国立国語研究所, 会期: 2018年9月4日-5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": "語彙多様性を評価する既存の指標には、延べ語数Nと異なり語数V(N)を入力とするもの、単語別の頻度を入力とするもの、単語列を入力とするものなどがある。本発表では、これらの指標の特徴を整理し、「現代日本語書き言葉均衡コーパス」(BCCWJ)を使用して指標値の分布を可視化する。NとV(N)を入力とする指標のいくつかは、両者の間に冪乗則V(N)=aNbを仮定している。TTRはb=1、Rはb=0.5としてaを指標値として利用するが、1では大きすぎ、0.5では小さすぎる。そこでV(N)とNの対数を単回帰分析してbの最適値を推定し、TTRを補正することを考える。実際には冪乗則は成立しないため、この補正は近似的だが、比較的簡単によい補正を得ることができる。この補正値を他の指標と比較し、テキストサイズが指標値の平均やばらつきに及ぼす影響を評価する。また、BCCWJの12のサブコーパスについてbの値を推定し、一覧で示す。", "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": "文部科学省", "subitem_description_type": "Other"}]}, "item_10003_description_52": {"attribute_name": "著者所属(英)", "attribute_value_mlt": [{"subitem_description": "Ministry of Education, Culture, Sports, Science and Technology", "subitem_description_type": "Other"}]}, "item_10003_identifier_registration": {"attribute_name": "ID登録", "attribute_value_mlt": [{"subitem_identifier_reg_text": "10.15084/00001686", "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2018"}], "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://pj.ninjal.ac.jp/corpus_center/lrw2018.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": "今田, 水穂"}, {"creatorName": "イマダ, ミズホ", "creatorNameLang": "ja-Kana"}, {"creatorName": "IMADA, Mizuho", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "4567", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "10579056", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000010579056"}, {"nameIdentifier": "imadamizuho", "nameIdentifierScheme": "researchmap", "nameIdentifierURI": "https://researchmap.jp/imadamizuho"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-02-14"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "LRW-2018-55-P-4-06.pdf", "filesize": [{"value": "3.8 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 3800000.0, "url": {"label": "LRW-2018-55-P-4-06.pdf", "url": "https://repository.ninjal.ac.jp/record/1702/files/LRW-2018-55-P-4-06.pdf"}, "version_id": "36009e02-20dd-4826-8591-9d3fdc8e1ad7"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "現代日本語書き言葉均衡コーパス(BCCWJ)", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Balanced Corpus of Contemporary Written Japanese (BCCWJ)", "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": "語彙多様性指標の可視化と単回帰分析によるTTRの補正", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "語彙多様性指標の可視化と単回帰分析によるTTRの補正"}, {"subitem_title": "Visualization of Lexical Diversity Indices and Adjustment of TTR by Single Regression Analysis", "subitem_title_language": "en"}]}, "item_type_id": "10003", "owner": "3", "path": ["268"], "permalink_uri": "https://doi.org/10.15084/00001686", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-02-14"}, "publish_date": "2019-02-14", "publish_status": "0", "recid": "1702", "relation": {}, "relation_version_is_last": true, "title": ["語彙多様性指標の可視化と単回帰分析によるTTRの補正"], "weko_shared_id": -1}