{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00048817","sets":["1164:4179:4250:4251"]},"path":["4251"],"owner":"1","recid":"48817","title":["英文契約書における内容の抽出　－シソーラス作成のための統計情報を用いた類似度計算－"],"pubdate":{"attribute_name":"公開日","attribute_value":"1998-11-05"},"_buckets":{"deposit":"2ce49364-2cbd-4878-a4a7-83ea79fa9d80"},"_deposit":{"id":"48817","pid":{"type":"depid","value":"48817","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"英文契約書における内容の抽出　－シソーラス作成のための統計情報を用いた類似度計算－","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"英文契約書における内容の抽出　－シソーラス作成のための統計情報を用いた類似度計算－"},{"subitem_title":"Information Extraction From an English Contract A statistics - based computation of word similarity for making a thesaurus for English contracts","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1998-11-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"奈良先端科学技術大学院大学情報科学研究科"},{"subitem_text_value":"奈良先端科学技術大学院大学情報科学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Information Science, Nara Institute of Science and Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science, Nara Institute of Science and Technology","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/48817/files/IPSJ-NL98128022.pdf"},"date":[{"dateType":"Available","dateValue":"2000-11-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL98128022.pdf","filesize":[{"value":"896.2 kB"}],"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":"1574e508-c41d-49b4-a086-b98929600f1f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1998 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"相良, かおる"},{"creatorName":"渡邊, 勝正"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kaoru, Sagara","creatorNameLang":"en"},{"creatorName":"Katsumasa, Watanabe","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":"本稿では、英文契約書に使われる単語の類似度を求める手法について提案する。本手法は、単語の共起頻度に基づく統計的手法の一種であり、内積を用いて類似度を定義している。本手法の特徴は、英文契約書の書式集の条文から、名詞ど動詞、動詞と名詞、形容詞と名詞、前置詞と名詞というように統語構造を意識した2つ組を求め、その2つ組間の関連度をベクトルの要素としている点にある。本手法により、英文契約書の書式集（162 298語）に含まれる名詞898種からなる209 274組のペアについて類似度を求め、数量化IV類によるクラス分けにより、81個のクラスの類概念データを作成した。なお、本研究は、英文契約書の内容抽出のための準備研究である。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes an approach for similarity measurement of words that are used in a collection of English contracts. This approach is a statistics-based computation of word similarity by a vector consisting of co-occurrence statistics. Using a vector consisting of the correlation between two-tuple of terms on the basis of syntactic behavior (such as the ordered pair verb, noun) is a feature of this approach. We made similarity data of 209,274 pairs from 898 nouns in the collection of English contracts, and made 81 classes from these similarity data with a multi-dimensional scaling. This work becomes a preparatory work for the information extraction from an English contract.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"166","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"159","bibliographicIssueDates":{"bibliographicIssueDate":"1998-11-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"99(1998-NL-128)","bibliographicVolumeNumber":"1998"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"updated":"2025-01-22T08:19:53.281363+00:00","created":"2025-01-18T23:13:58.431219+00:00","links":{},"id":48817}