{"created":"2021-03-01T06:16:56.963121+00:00","id":409,"links":{},"metadata":{"_buckets":{"deposit":"e03df6cb-240c-4fed-8622-1e6f295ada72"},"_deposit":{"id":"409","owners":[],"pid":{"revision_id":0,"type":"depid","value":"409"},"status":"published"},"_oai":{"id":"oai:repository.dl.itc.u-tokyo.ac.jp:00000409","sets":["34:95:96","9:10:15"]},"item_2_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Analysis on Difficulty Indices for Japanese Named Entity Task"}]},"item_2_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2003-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicPageEnd":"26","bibliographicPageStart":"3","bibliographicVolumeNumber":"10","bibliographic_titles":[{"bibliographic_title":"自然言語処理"}]}]},"item_2_description_13":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_2_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"本論文では，固有表現抽出の難易度をテストコーパスから評価する指標を提案する．固有表現抽出システムの性能は客観的な指標によって評価される．しかし，システムの出力に対する評価だけでは，あるコーパスに対する固有表現抽出がどのように難しいのか，どのような情報がそのコーパスに対して固有表現抽出を行なう際に有効なのかを知ることは難しい．本論文で提案する指標は，個々のシステムの出力に依存することなく，複数のコーパスについて統一的に適用できる．指標の有効性は固有表現抽出システムの性能評価と比較することで検証される．さらに固有表現のクラス間における難易度の比較や，有用な情報の違いについても議論する．","subitem_description_type":"Abstract"},{"subitem_description":"We propose indices to measure the difficulty of the named entity (NE) task by looking at test corpora, based on expressions inside and outside the NEs. These indices are intended to estimate the difficulty of each task without actually using an NE system and to be unbiased towards a specific system. The values of the indices are compared with the systems’ performance in Japanese documents. We also discuss the difference between NE classes with the indices and show useful clues which will make it easier to recognize NEs.","subitem_description_type":"Abstract"}]},"item_2_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"106320","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Nobata, Chikashi"}]},{"nameIdentifiers":[{"nameIdentifier":"106321","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Sekine, Satoshi"}]},{"nameIdentifiers":[{"nameIdentifier":"106322","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Tsujii, Jun’ichi"}]}]},"item_2_publisher_20":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"言語処理学会"}]},"item_2_source_id_10":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10472659","subitem_source_identifier_type":"NCID"}]},"item_2_source_id_8":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"13407619","subitem_source_identifier_type":"ISSN"}]},"item_2_subject_15":{"attribute_name":"日本十進分類法","attribute_value_mlt":[{"subitem_subject":"007","subitem_subject_scheme":"NDC"}]},"item_2_text_21":{"attribute_name":"出版者別名","attribute_value_mlt":[{"subitem_text_value":"The Association for Natural Language Processing"}]},"item_2_text_4":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"独立行政法人通信総合研究所けいはんな情報融合研究センター自然言語グループ"},{"subitem_text_value":"ニューヨーク大学コンピュータサイエンス学科"},{"subitem_text_value":"東京大学大学院情報理工学系研究科コンピュータ科学専攻"},{"subitem_text_value":"Computational Linguistic Group, Keihanna Human Info-Communication Research Center, Communications Research Laboratory"},{"subitem_text_value":"Computer Science Department, New York University"},{"subitem_text_value":"Graduate school of Information Science and Technology, University of Tokyo"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"野畑, 周"}],"nameIdentifiers":[{"nameIdentifier":"106317","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"関根, 聡"}],"nameIdentifiers":[{"nameIdentifier":"106318","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"辻井, 潤一"}],"nameIdentifiers":[{"nameIdentifier":"106319","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":"2017-06-26"}],"displaytype":"detail","filename":"v10n1_01.pdf","filesize":[{"value":"185.9 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"v10n1_01.pdf","url":"https://repository.dl.itc.u-tokyo.ac.jp/record/409/files/v10n1_01.pdf"},"version_id":"bae08c1b-749e-4e31-b73b-3b4e27687045"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"固有表現","subitem_subject_scheme":"Other"},{"subitem_subject":"情報抽出","subitem_subject_scheme":"Other"},{"subitem_subject":"コーパス比較","subitem_subject_scheme":"Other"},{"subitem_subject":"Named entity","subitem_subject_scheme":"Other"},{"subitem_subject":"Information extraction","subitem_subject_scheme":"Other"},{"subitem_subject":"Corpus comparison","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":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"日本語固有表現抽出の難易度を示す指標の提案と評価","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"日本語固有表現抽出の難易度を示す指標の提案と評価"}]},"item_type_id":"2","owner":"1","path":["15","96"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-12-08"},"publish_date":"2009-12-08","publish_status":"0","recid":"409","relation_version_is_last":true,"title":["日本語固有表現抽出の難易度を示す指標の提案と評価"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-19T03:41:13.563465+00:00"}