{"created":"2021-03-01T06:16:57.513792+00:00","id":418,"links":{},"metadata":{"_buckets":{"deposit":"85a6e81a-cf8e-4df6-a270-d7988c870997"},"_deposit":{"id":"418","owners":[],"pid":{"revision_id":0,"type":"depid","value":"418"},"status":"published"},"_oai":{"id":"oai:repository.dl.itc.u-tokyo.ac.jp:00000418","sets":["12:13","9:10:15"]},"item_2_alternative_title_1":{"attribute_name":"その他のタイトル","attribute_value_mlt":[{"subitem_alternative_title":"Term Extraction Based on Occurrence and Concatenation Frequency"}]},"item_2_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2003-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicPageEnd":"46","bibliographicPageStart":"27","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，専門用語を専門分野コーパスから自動抽出する方法の提案と実験的評価を報告する．本論文では名詞(単名詞と複合名詞) を対象として専門用語抽出について検討する．基本的アイデアは，単名詞のバイグラムから得られる単名詞の統計量を利用するという点である．より具体的に言えば，ある単名詞が複合名詞を形成するために連接する名詞の頻度を用いる．この頻度を利用した数種類の複合名詞スコア付け法を提案する．NTCIR1 TMREC テストコレクションによって提案方法を実験的に評価した．この結果，スコアの上位の1,400 用語候補以内，ならびに，12,000 用語候補以上においては，単名詞バイグラムの統計に基づく提案手法が優れていることがわかった．","subitem_description_type":"Abstract"},{"subitem_description":"In this paper, we propose a new idea of automatically recognizing domain specific terms from monolingual corpus. The majority of domain specific terms are compound nouns that we aim at extracting. Our idea is based on single-noun statistics calculated with single-noun bigrams. Namely we focus on how many nouns adjoin the noun in question to form compound nouns. In addition, we combine this measure and frequency of each compound nouns and single-nouns, which we call FLR method. We experimentally evaluate these methods on NTCIR1 TMREC test collection. As the results, when we take into account less than 1,400 or more than 12,000 highest term candidates, FLR method performs best.","subitem_description_type":"Abstract"}]},"item_2_full_name_3":{"attribute_name":"著者別名","attribute_value_mlt":[{"nameIdentifiers":[{"nameIdentifier":"106362","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Nakagawa, Hiroshi"}]},{"nameIdentifiers":[{"nameIdentifier":"106363","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Yumoto, Hiroaki"}]},{"nameIdentifiers":[{"nameIdentifier":"106364","nameIdentifierScheme":"WEKO"}],"names":[{"name":"Mori, Tatsunori"}]}]},"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":"東京大学情報基盤センター"},{"subitem_text_value":"横浜国立大学大学院工学研究科"},{"subitem_text_value":"横浜国立大学大学院環境情報研究院"},{"subitem_text_value":"株式会社東芝"},{"subitem_text_value":"東芝IT ソリューション株式会社"},{"subitem_text_value":"Information Technology Center, the University of Tokyo"},{"subitem_text_value":"Graduate School of Engineering, Yokohama National University"},{"subitem_text_value":"Graduate School of Environment and Information Sciences, Yokohama National University"},{"subitem_text_value":"Toshiba IT-Solutions Corporation"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"中川, 裕志"}],"nameIdentifiers":[{"nameIdentifier":"106359","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"湯本, 紘彰"}],"nameIdentifiers":[{"nameIdentifier":"106360","nameIdentifierScheme":"WEKO"}]},{"creatorNames":[{"creatorName":"森, 辰則"}],"nameIdentifiers":[{"nameIdentifier":"106361","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_02.pdf","filesize":[{"value":"283.5 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"v10n1_02.pdf","url":"https://repository.dl.itc.u-tokyo.ac.jp/record/418/files/v10n1_02.pdf"},"version_id":"762eaeac-e4b8-494d-8b40-761ec110acee"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"用語抽出","subitem_subject_scheme":"Other"},{"subitem_subject":"専門用語","subitem_subject_scheme":"Other"},{"subitem_subject":"単名詞","subitem_subject_scheme":"Other"},{"subitem_subject":"複合名詞","subitem_subject_scheme":"Other"},{"subitem_subject":"Term recognition","subitem_subject_scheme":"Other"},{"subitem_subject":"Domain specific terms","subitem_subject_scheme":"Other"},{"subitem_subject":"Basic Nouns","subitem_subject_scheme":"Other"},{"subitem_subject":"Compound Nouns","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":"出現頻度と連接頻度に基づく専門用語抽出","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"出現頻度と連接頻度に基づく専門用語抽出"}]},"item_type_id":"2","owner":"1","path":["13","15"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-12-15"},"publish_date":"2009-12-15","publish_status":"0","recid":"418","relation_version_is_last":true,"title":["出現頻度と連接頻度に基づく専門用語抽出"],"weko_creator_id":"1","weko_shared_id":null},"updated":"2022-12-19T03:41:16.382902+00:00"}