{"_buckets": {"deposit": "b923f5bd-fe43-4df7-bc94-58016161e179"}, "_deposit": {"created_by": 3, "id": "531", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "531"}, "status": "published"}, "_oai": {"id": "oai:repository.ninjal.ac.jp:00000531", "sets": ["66"]}, "author_link": ["6301", "6302", "6296", "6293", "6294", "6295", "6298", "6300", "6299", "6297"], "item_10002_biblio_info_40": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2014-05", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "7", "bibliographicPageEnd": "26", "bibliographicPageStart": "1", "bibliographic_titles": [{"bibliographic_title": "国立国語研究所論集"}, {"bibliographic_title": "NINJAL Research Papers", "bibliographic_titleLang": "en"}]}]}, "item_10002_description_34": {"attribute_name": "著者所属", "attribute_value_mlt": [{"subitem_description": "国立国語研究所 コーパス開発センター", "subitem_description_type": "Other"}, {"subitem_description": "国立国語研究所 コーパス開発センター プロジェクト研究員", "subitem_description_type": "Other"}, {"subitem_description": "国立国語研究所 コーパス開発センター プロジェクト研究員", "subitem_description_type": "Other"}, {"subitem_description": "国立国語研究所 コーパス開発センター 非常勤研究員", "subitem_description_type": "Other"}, {"subitem_description": "国立国語研究所 言語資源研究系", "subitem_description_type": "Other"}]}, "item_10002_description_35": {"attribute_name": "著者所属(英)", "attribute_value_mlt": [{"subitem_description": "Center for Corpus Development, NINJAL", "subitem_description_type": "Other"}, {"subitem_description": "Postdoctoral Research Fellow, Center for Corpus Development, NINJAL", "subitem_description_type": "Other"}, {"subitem_description": "Postdoctoral Research Fellow, Center for Corpus Development, NINJAL", "subitem_description_type": "Other"}, {"subitem_description": "Adjunct Researcher, Center for Corpus Development, NINJAL", "subitem_description_type": "Other"}, {"subitem_description": "Department of Corpus Studies, NINJAL", "subitem_description_type": "Other"}]}, "item_10002_description_36": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "国立国語研究所コーパス開発センターでは2011年より超大規模コーパスプロジェクトとして,Webを母集団とした100億語規模のコーパスの構築を進めている。構築にあたっては,工程を収集・組織化・利活用・保存の四つに分割して実装を進めている。本論文ではそのうち最初の2工程について報告する。収集に関しては,2012年第4四半期より3か月ごとに1億URLのクロールを繰り返し実施している。また組織化に関しては,2013年第3四半期までの約1年間に収集されたWebページの文抽出・形態素解析・係り受け解析を実施した。これらの作業に生じた問題とその解決法を示した後,2013年末において構築されたコーパスデータの基礎統計量を示し,本コーパスを用いてどのような理論的・応用的研究が可能になると考えられるかを論じる。", "subitem_description_type": "Abstract"}]}, "item_10002_description_37": {"attribute_name": "抄録(英)", "attribute_value_mlt": [{"subitem_description": "In 2011, the National Institute for Japanese Language and Linguistics launched a corpus compilation project with the aim of constructing a ten-billion-word Web corpus. The project was split into the following four sub-projects: page collection, linguistic annotation, release, and preservation. During the page collection stage, crawling began during the fourth quarter of 2012. We crawled 100 million URLs every three months as fixed-point observations. During the linguistic annotation, normalization (HTML tag removal and character encoding conversion), Japanese morphological analysis (word segmentation and part-of-speech tagging), and Japanese dependency analysis were performed on the data that were crawled in the timespan of one year, specifically from the fourth quarter of 2012 to the third quarter of 2013. In this paper, we present the basic statistics of the crawled data and discuss possible theoretical and practical implications of the language resources. Additionally, we address issues encountered during the page collection and linguistic annotation stages, and offer tentative solutions.", "subitem_description_type": "Other"}]}, "item_10002_description_51": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_10002_identifier_registration": {"attribute_name": "ID登録", "attribute_value_mlt": [{"subitem_identifier_reg_text": "10.15084/00000522", "subitem_identifier_reg_type": "JaLC"}]}, "item_10002_publisher_39": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "国立国語研究所"}]}, "item_10002_source_id_41": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "2186-134X", "subitem_source_identifier_type": "ISSN"}, {"subitem_source_identifier": "2186-1358", "subitem_source_identifier_type": "ISSN"}]}, "item_10002_source_id_44": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AA12536262", "subitem_source_identifier_type": "NCID"}]}, "item_10002_title_29": {"attribute_name": "タイトル（ヨミ）", "attribute_value_mlt": [{"subitem_title": "Web オ ボシュウダン ト シタ チョウ ダイキボ コーパス ノ カイハツ シュウシュウ ト ソシキカ"}]}, "item_10002_version_type_52": {"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": "浅原, 正幸"}, {"creatorName": "アサハラ, マサユキ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "6293", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "今田, 水穂"}, {"creatorName": "イマダ, ミズホ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "6294", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "保田, 祥"}, {"creatorName": "ヤスダ, サチ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "6295", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "小西, 光"}, {"creatorName": "コニシ, ヒカリ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "6296", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "前川, 喜久雄"}, {"creatorName": "マエカワ, キクオ", "creatorNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "6297", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "ASAHARA, Masayuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "6298", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "IMADA, Mizuho", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "6299", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "YASUDA, Sachi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "6300", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "KONISHI, Hikari", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "6301", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "MAEKAWA, Kikuo", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "6302", "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": "2019-02-20"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "papers0701.pdf", "filesize": [{"value": "2.0 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 2000000.0, "url": {"label": "papers0701.pdf", "url": "https://repository.ninjal.ac.jp/record/531/files/papers0701.pdf"}, "version_id": "0b796069-a70c-49d5-89e4-8ea17330802d"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "コーパス構築", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Webアーカイブ", "subitem_subject_scheme": "Other"}, {"subitem_subject": "言語情報組織化", "subitem_subject_scheme": "Other"}, {"subitem_subject": "言語解析", "subitem_subject_scheme": "Other"}, {"subitem_subject": "corpus development", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "web archive", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "linguistic information indexing", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "linguistic analyzers", "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": "departmental bulletin paper", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Webを母集団とした超大規模コーパスの開発 : 収集と組織化", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Webを母集団とした超大規模コーパスの開発 : 収集と組織化"}, {"subitem_title": "Page Collection and Linguistic Annotation Issues in Ultra Large-Scale Web Corpus Construction", "subitem_title_language": "en"}]}, "item_type_id": "10002", "owner": "3", "path": ["66"], "permalink_uri": "https://doi.org/10.15084/00000522", "pubdate": {"attribute_name": "公開日", "attribute_value": "2015-10-30"}, "publish_date": "2015-10-30", "publish_status": "0", "recid": "531", "relation": {}, "relation_version_is_last": true, "title": ["Webを母集団とした超大規模コーパスの開発 : 収集と組織化"], "weko_shared_id": -1}