{"created":"2025-01-18T23:14:19.285258+00:00","updated":"2025-01-22T08:06:40.554855+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00049268","sets":["1164:4179:4278:4281"]},"path":["4281"],"owner":"1","recid":"49268","title":["単語ベクトルを用いた多義語の意味推定　－共起ベクトルと定義距離ベクトルの比較－"],"pubdate":{"attribute_name":"公開日","attribute_value":"1994-07-21"},"_buckets":{"deposit":"bf710a39-44ac-4ca4-9776-b4ee3580c44d"},"_deposit":{"id":"49268","pid":{"type":"depid","value":"49268","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"単語ベクトルを用いた多義語の意味推定　－共起ベクトルと定義距離ベクトルの比較－","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"単語ベクトルを用いた多義語の意味推定　－共起ベクトルと定義距離ベクトルの比較－"},{"subitem_title":"Word Sense Disambiguation using Word Vectors : Co - occurrence Vectors vs. Definition - Distance Vectors","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1994-07-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"（株）日立製作所、基礎研究所"},{"subitem_text_value":"（株）日立製作所、基礎研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Advanced Research Laboratory, Hitachi, Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Advanced Research Laboratory, Hitachi, Ltd.","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/49268/files/IPSJ-NL94102007.pdf"},"date":[{"dateType":"Available","dateValue":"1996-07-21"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL94102007.pdf","filesize":[{"value":"1.2 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":"a6c45b82-7e90-4406-a061-5b6a9608354a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1994 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"丹羽, 芳樹"},{"creatorName":"新田, 義彦"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yoshiki, Niwa","creatorNameLang":"en"},{"creatorName":"Yoshihiko, Nitta","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":"実用的な自然言語処理に求められる頑健性を確保するためには、ルールに基づく解析を補う数値計算的手段が有効である。単語ベクトルとは単語の意味を反映した座標表現であり、文脈の類似度計算や単語例からの学習など幅広い応用が期待される。本研究では2種類の単語ベクトルを用い、多義語の意味推定問題での効果を比較した。一つは大規模テキストから共起統計により得られる共起ベクトル、もう一つは辞書の語義から計算される単語間距離を用いる定義距離ベクトルである。9種類の多義語に関する実験結果では共起ベクトルの方が高い正解率が得られた。従って文脈の類似度に基づく多義性解消問題に関しては共起ベクトルを用いた方が有利である。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"A comparison was made of vectors derived by using ordinary co-occurrence statistics from large text corpora and of vectors derived by measuring the inter-word distances in dictionary definitions. The precision of word sense disambiguation by using co-occurrence vectors from the 1987 Wall Street Journal (20M total words) was higher than that by using distance vectors from the Collins English Dictionary (60K head words + 1.6M definition words). Therefore, co-occurrence vectors are advantageous over definition distance vectors to WSD based on the context similarity.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"56","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"49","bibliographicIssueDates":{"bibliographicIssueDate":"1994-07-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"63(1994-NL-102)","bibliographicVolumeNumber":"1994"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":49268,"links":{}}