{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00147214","sets":["1164:4179:8454:8455"]},"path":["8455"],"owner":"11","recid":"147214","title":["分散表現に基づく選択選好モデルの文脈化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-01-15"},"_buckets":{"deposit":"b9131c54-e1b9-43a1-9e8e-897f011f1a1b"},"_deposit":{"id":"147214","pid":{"type":"depid","value":"147214","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"分散表現に基づく選択選好モデルの文脈化","author_link":["233080","233083","233079","233081","233082"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"分散表現に基づく選択選好モデルの文脈化"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"意味解析・形態素解析","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2016-01-15","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東北大学大学院情報科学研究科"},{"subitem_text_value":"東北大学大学院情報科学研究科"},{"subitem_text_value":"東北大学大学院情報科学研究科"},{"subitem_text_value":"東北大学大学院情報科学研究科"},{"subitem_text_value":"東北大学大学院情報科学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","subitem_text_language":"en"},{"subitem_text_value":"Tohoku University","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/147214/files/IPSJ-NL16225001.pdf","label":"IPSJ-NL16225001.pdf"},"date":[{"dateType":"Available","dateValue":"2018-01-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL16225001.pdf","filesize":[{"value":"399.2 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":"f8b5c050-2064-4686-96ce-56b0677357ef","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大野, 雅之"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"井之上, 直也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"松林, 優一郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"岡崎, 直観"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"乾, 健太郎"}],"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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"述語の選択選好性のモデル化は，述語項構造解析・省略解析を始めとした意味解析において重要な基盤技術の一つである．これまでの研究では，「述語の選択選好性は項となる名詞の意味的な性質にのみ依拠する」 という仮定して選好性を学習してきた （e.g., man は arrest の目的語になりうる）．省略解析などの談話解析への応用を考えると，談話内での名詞の言及のされ方まで含めて選好性を計算できることが望ましい （e.g., 悪事を犯した man は arrest の目的語になりうるが，善良な man はなりにくい）．そこで本研究では，ニューラルネットワークに基づく選択選好モデル [Van de Cruys 2014] を拡張し，名詞の意味的な性質に加え，談話内での言及のされ方を分散表現で表現することにより，名詞の出現文脈を考慮した述語の選択選好モデルを提案する．評価実験では，代名詞照応解析への応用を見据え，代名詞に対する先行詞候補のランキング問題に基づく評価を行い，名詞の出現文脈を用いることの有効性を確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"9","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2016-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2016-NL-225"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":147214,"updated":"2025-01-20T17:41:47.279241+00:00","links":{},"created":"2025-01-19T00:22:25.748256+00:00"}