{"updated":"2025-01-22T08:29:15.337666+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00048485","sets":["1164:4179:4229:4231"]},"path":["4231"],"owner":"1","recid":"48485","title":["出現頻度と連接頻度に基づく専門用語抽出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2001-09-10"},"_buckets":{"deposit":"a4e6d7cd-d3d3-4180-a908-060db239eae6"},"_deposit":{"id":"48485","pid":{"type":"depid","value":"48485","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"出現頻度と連接頻度に基づく専門用語抽出","author_link":["0","0"],"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"},{"subitem_title":"Term Extraction Based on Occurrence and Concatenation Frequency","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2001-09-10","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"横浜国立大学"},{"subitem_text_value":"横浜国立大学"},{"subitem_text_value":"東京大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Yokohama National University","subitem_text_language":"en"},{"subitem_text_value":"Yokohama National University","subitem_text_language":"en"},{"subitem_text_value":"University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/48485/files/IPSJ-NL01145017.pdf"},"date":[{"dateType":"Available","dateValue":"2003-09-10"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL01145017.pdf","filesize":[{"value":"1.4 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"570e06df-8ff5-4f04-aac9-0786df51aa52","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2001 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"湯本, 紘彰"},{"creatorName":"森, 辰則"},{"creatorName":"中川, 裕志"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hiroaki, Yumoto","creatorNameLang":"en"},{"creatorName":"Tatsunori, Mori","creatorNameLang":"en"},{"creatorName":"Hiroshi, Nakagawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","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た。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"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 statistic calculated with single-noun bigrams. Namely we focus on how many nouns adjoin the noun in question to form compound nouns. In adition, we combine thismeasure and frequency of each compound nouns and single-nouns, whichwe call FLR method. We experimentally evaluate these methodson NTCIR1 TMREC test collection. As the results, when we take intoaccount up to 1,400 highest term candidates, FLR method performsbest.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"118","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"111","bibliographicIssueDates":{"bibliographicIssueDate":"2001-09-10","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"86(2001-NL-145)","bibliographicVolumeNumber":"2001"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:13:43.235050+00:00","id":48485,"links":{}}