{"updated":"2025-01-22T07:59:14.034712+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00049581","sets":["1164:4179:4306:4309"]},"path":["4309"],"owner":"1","recid":"49581","title":["超並列制約伝播による自然言語処理の手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"1990-07-19"},"_buckets":{"deposit":"923b792b-85b6-4346-bdce-ddf40276919c"},"_deposit":{"id":"49581","pid":{"type":"depid","value":"49581","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"超並列制約伝播による自然言語処理の手法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"超並列制約伝播による自然言語処理の手法"},{"subitem_title":"Massively - Parallel Constraint Propagation as a Paradigm for Natural Language Processing","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1990-07-19","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"ATR自動翻訳電話研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Visiting Research Scientist from Center for Machine Translation, Carnegie Mellon 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/49581/files/IPSJ-NL90078002.pdf"},"date":[{"dateType":"Available","dateValue":"1992-07-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL90078002.pdf","filesize":[{"value":"1.5 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":"e6ad51b2-ac89-459a-a2cd-0443c81170c7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1990 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"苫米地, 英人"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Hideto, Tomabechi","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":"記号的および非記号的な制約の超並列活性化ネットワーク上での伝播による自然言語処理の手法について述べる。この手法は既存の活性化マーカ伝播による方法と異なり、複雑な言語的制約を必要とする言語現象を扱うことを可能とする。また、軽量並列プロセスを利用することにより並列計算機上に超並列制約伝播処理を実現する手法を示す。この手法により、密結合共有メモリ型並列計算機上にて完全分散型の神経回路網と記号的制約伝播ネットを共存させることが可能となる。更に既存の解析法と異なり、文法知識の増大による複雑さの増大の問題が軽量並列プロセス数の増加で対処可能となる。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We propose a model of natural language processing based on a paradigm of massively parallel (symbolic/subsymbolic) constraint propagation. It differs from the traditional spreading-activation marker-passing schemes in its capacity to handle linguistic phenomena that require application of complex grammatical constraints. We also discuss a scheme of realizing massively parallel constraint propagation activity on a parallel machine hardware through the use of light weight processes while retaining the capacity to integrate fully-distributed contextual and acoustic recognitions. Unlike existing parsing schemes, in our model, the increase in the size of grammar can be directly countered through an increase in number of parallel light weight processes.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"16","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告自然言語処理（NL）"}],"bibliographicPageStart":"9","bibliographicIssueDates":{"bibliographicIssueDate":"1990-07-19","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"64(1990-NL-078)","bibliographicVolumeNumber":"1990"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"created":"2025-01-18T23:14:33.716276+00:00","id":49581,"links":{}}