ログイン
言語:

WEKO3

  • トップ
  • コミュニティ
  • ランキング
AND
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "5655ec72-9aae-4857-93bf-94610b6c4440"}, "_deposit": {"id": "411", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "411"}, "status": "published"}, "_oai": {"id": "oai:repository.dl.itc.u-tokyo.ac.jp:00000411"}, "item_2_alternative_title_1": {"attribute_name": "\u305d\u306e\u4ed6\u306e\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_alternative_title": "Estimating reliability of rules in decision lists using Bayesian learning"}]}, "item_2_biblio_info_7": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2002-04", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "3", "bibliographicPageEnd": "19", "bibliographicPageStart": "3", "bibliographicVolumeNumber": "9", "bibliographic_titles": [{"bibliographic_title": "\u81ea\u7136\u8a00\u8a9e\u51e6\u7406"}]}]}, "item_2_description_13": {"attribute_name": "\u30d5\u30a9\u30fc\u30de\u30c3\u30c8", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_2_description_5": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "\u7d71\u8a08\u7684\u30af\u30e9\u30b9\u5206\u985e\u5668\u3068\u3057\u3066\u306e\u6c7a\u5b9a\u30ea\u30b9\u30c8\u306f\uff0c\u8fd1\u5e74\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u306b\u304a\u3051\u308b\u69d8\u3005\u306a\u5206\u91ce\u3067\u305d\u306e\u6709\u52b9\u6027\u3092\u793a\u3057\u3066\u3044\u308b\uff0e\u6c7a\u5b9a\u30ea\u30b9\u30c8\u3092\u69cb\u6210\u3059\u308b\u4e0a\u3067\u6700\u3082\u91cd\u8981\u306a\u554f\u984c\u306e\u4e00\u3064\u306f\uff0c\u30eb\u30fc\u30eb\u306e\u4fe1\u983c\u5ea6\u306e\u7b97\u51fa\u6cd5\u3067\u3042\u308b\uff0e\u6c7a\u5b9a\u30ea\u30b9\u30c8\u3092\u7528\u3044\u305f\u591a\u304f\u306e\u7814\u7a76\u3067\u306f\uff0c\u6700\u5c24\u63a8\u5b9a\u6cd5\u3068\u7c21\u5358\u306a\u30b9\u30e0\u30fc\u30b8\u30f3\u30b0\u306b\u3088\u308a\u4fe1\u983c\u5ea6\u3092\u7b97\u51fa\u3057\u3066\u3044\u308b\u304c\uff0c\u7406\u8ad6\u7684\u306a\u6839\u62e0\u306b\u6b20\u3051\u63a8\u5b9a\u7cbe\u5ea6\u3082\u9ad8\u304f\u306a\u3044\u3068\u3044\u3046\u554f\u984c\u304c\u3042\u308b\uff0e\u305d\u3053\u3067\u672c\u8ad6\u6587\u3067\u306f\uff0c\u30d9\u30a4\u30ba\u5b66\u7fd2\u6cd5\u3092\u5229\u7528\u3057\u3066\u30eb\u30fc\u30eb\u306e\u4fe1\u983c\u5ea6\u3092\u7b97\u51fa\u3059\u308b\u624b\u6cd5\u3092\u793a\u3059\uff0e\u3055\u3089\u306b\uff0c\u8a3c\u62e0\u306e\u7a2e\u985e\u3054\u3068\u306b\u7570\u306a\u308b\u4e8b\u524d\u5206\u5e03\u3092\u5229\u7528\u3059\u308b\u3053\u3068\u3067\uff0c\u3088\u308a\u6b63\u78ba\u306a\u4fe1\u983c\u5ea6\u306e\u63a8\u5b9a\u304c\u53ef\u80fd\u306b\u306a\u308a\uff0c\u6c7a\u5b9a\u30ea\u30b9\u30c8\u306e\u6027\u80fd\u304c\u5411\u4e0a\u3059\u308b\u3053\u3068\u3092\u793a\u3059\uff0e\u672c\u624b\u6cd5\u306e\u6709\u52b9\u6027\u3092\u78ba\u304b\u3081\u308b\u305f\u3081\u306b\uff0c\u8a9e\u7fa9\u66d6\u6627\u6027\u89e3\u6d88\u306e\u554f\u984c\u306b\u6c7a\u5b9a\u30ea\u30b9\u30c8\u3092\u9069\u7528\u3057\u3066\u5b9f\u9a13\u3092\u884c\u306a\u3063\u305f\uff0e\u82f1\u8a9e\u306b\u95a2\u3057\u3066\u306fSenseval-1 \u306e\u30c7\u30fc\u30bf\u3092\u7528\u3044\uff0c\u65e5\u672c\u8a9e\u306b\u95a2\u3057\u3066\u306f\u7591\u4f3c\u5358\u8a9e\u3092\u7528\u3044\u305f\uff0e\u305d\u306e\u7d50\u679c\uff0c\u30d9\u30a4\u30ba\u5b66\u7fd2\u306b\u3088\u308b\u4fe1\u983c\u5ea6\u63a8\u5b9a\u624b\u6cd5\u304c\uff0c\u30eb\u30fc\u30eb\u306e\u78ba\u7387\u5024\u306e\u63a8\u5b9a\u7cbe\u5ea6\u3092\u9ad8\u3081\uff0c\u6c7a\u5b9a\u30ea\u30b9\u30c8\u306e\u5206\u985e\u6027\u80fd\u3092\u5411\u4e0a\u3055\u305b\u308b\u3053\u3068\u3092\u78ba\u8a8d\u3057\u305f\uff0e", "subitem_description_type": "Abstract"}, {"subitem_description": "The decision list algorithm is one of the most successful algorithms for classification problems in natural language processing. The most important part of the decision list algorithm is the calculation of reliability for each rule, hence the estimation of probability for each contextual evidence. However, the majority of research efforts using decision lists do not think much of the estimation method. We propose an estimation method based on Bayesian learning which gives well-founded smoothing and better use of prior information on each type of contextual evidences. Experimental results obtained using Senseval-1 data set and Japanese pseudowords show that our method makes probability estimation more precise, leading to improvement of classification performance of the decision list algorithm.", "subitem_description_type": "Abstract"}]}, "item_2_full_name_3": {"attribute_name": "\u8457\u8005\u5225\u540d", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "106333", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Tsuruoka, Yoshimasa"}]}, {"nameIdentifiers": [{"nameIdentifier": "106334", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Chikayama, Takashi"}]}]}, "item_2_publisher_20": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "\u8a00\u8a9e\u51e6\u7406\u5b66\u4f1a"}]}, "item_2_source_id_10": {"attribute_name": "\u66f8\u8a8c\u30ec\u30b3\u30fc\u30c9ID", "attribute_value_mlt": [{"subitem_source_identifier": "AN10472659", "subitem_source_identifier_type": "NCID"}]}, "item_2_source_id_8": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "13407619", "subitem_source_identifier_type": "ISSN"}]}, "item_2_subject_15": {"attribute_name": "\u65e5\u672c\u5341\u9032\u5206\u985e\u6cd5", "attribute_value_mlt": [{"subitem_subject": "007", "subitem_subject_scheme": "NDC"}]}, "item_2_text_21": {"attribute_name": "\u51fa\u7248\u8005\u5225\u540d", "attribute_value_mlt": [{"subitem_text_value": "The Association for Natural Language Processing"}]}, "item_2_text_34": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"subitem_text_value": "Journal Article"}]}, "item_2_text_4": {"attribute_name": "\u8457\u8005\u6240\u5c5e", "attribute_value_mlt": [{"subitem_text_value": "\u79d1\u5b66\u6280\u8853\u632f\u8208\u4e8b\u696d\u56e3"}, {"subitem_text_value": "\u6771\u4eac\u5927\u5b66\u65b0\u9818\u57df\u5275\u6210\u79d1\u5b66\u7814\u7a76\u79d1"}, {"subitem_text_value": "Japan Science and Technology Corporation"}, {"subitem_text_value": "School of Frontier Sciences, The University of Tokyo"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "\u9db4\u5ca1, \u6176\u96c5"}], "nameIdentifiers": [{"nameIdentifier": "106331", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u8fd1\u5c71, \u9686"}], "nameIdentifiers": [{"nameIdentifier": "106332", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "\u30d5\u30a1\u30a4\u30eb\u60c5\u5831", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2017-06-26"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "v09n3_01.pdf", "filesize": [{"value": "136.7 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 136700.0, "url": {"label": "\u672c\u6587(fulltext)", "url": "https://repository.dl.itc.u-tokyo.ac.jp/record/411/files/v09n3_01.pdf"}, "version_id": "21a1c061-8e5c-489b-bf00-20b41f831b3a"}]}, "item_keyword": {"attribute_name": "\u30ad\u30fc\u30ef\u30fc\u30c9", "attribute_value_mlt": [{"subitem_subject": "\u6c7a\u5b9a\u30ea\u30b9\u30c8", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u30d9\u30a4\u30ba\u5b66\u7fd2", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u4e8b\u524d\u5206\u5e03", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u8a9e\u8b70\u66d6\u6627\u6027\u89e3\u6d88", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Decision lists", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Bayesian learning", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Prior distribution", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Word sense disambiguation", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "\u30d9\u30a4\u30ba\u7d71\u8a08\u306e\u624b\u6cd5\u3092\u5229\u7528\u3057\u305f\u6c7a\u5b9a\u30ea\u30b9\u30c8\u306e\u30eb\u30fc\u30eb\u4fe1\u983c\u5ea6\u63a8\u5b9a\u6cd5", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "\u30d9\u30a4\u30ba\u7d71\u8a08\u306e\u624b\u6cd5\u3092\u5229\u7528\u3057\u305f\u6c7a\u5b9a\u30ea\u30b9\u30c8\u306e\u30eb\u30fc\u30eb\u4fe1\u983c\u5ea6\u63a8\u5b9a\u6cd5"}]}, "item_type_id": "2", "owner": "1", "path": ["9/10/15", "110/111/112"], "permalink_uri": "http://hdl.handle.net/2261/29408", "pubdate": {"attribute_name": "\u516c\u958b\u65e5", "attribute_value": "2009-12-14"}, "publish_date": "2009-12-14", "publish_status": "0", "recid": "411", "relation": {}, "relation_version_is_last": true, "title": ["\u30d9\u30a4\u30ba\u7d71\u8a08\u306e\u624b\u6cd5\u3092\u5229\u7528\u3057\u305f\u6c7a\u5b9a\u30ea\u30b9\u30c8\u306e\u30eb\u30fc\u30eb\u4fe1\u983c\u5ea6\u63a8\u5b9a\u6cd5"], "weko_shared_id": null}
  1. 122 新領域創成科学研究科
  2. 13 基盤科学研究系 基盤情報学専攻
  3. 1221310 学術雑誌論文
  1. 0 資料タイプ別
  2. 10 学術雑誌論文
  3. 010 総記

ベイズ統計の手法を利用した決定リストのルール信頼度推定法

http://hdl.handle.net/2261/29408
7b3bed54-45b7-4237-86e8-cbf59404db80
名前 / ファイル ライセンス アクション
v09n3_01.pdf 本文(fulltext) (136.7 kB)
Item type 学術雑誌論文 / Journal Article(1)
公開日 2009-12-14
タイトル
タイトル ベイズ統計の手法を利用した決定リストのルール信頼度推定法
言語
言語 jpn
キーワード
主題 決定リスト
主題Scheme Other
キーワード
主題 ベイズ学習
主題Scheme Other
キーワード
主題 事前分布
主題Scheme Other
キーワード
主題 語議曖昧性解消
主題Scheme Other
キーワード
主題 Decision lists
主題Scheme Other
キーワード
主題 Bayesian learning
主題Scheme Other
キーワード
主題 Prior distribution
主題Scheme Other
キーワード
主題 Word sense disambiguation
主題Scheme Other
資源タイプ
資源 http://purl.org/coar/resource_type/c_6501
タイプ journal article
その他のタイトル
その他のタイトル Estimating reliability of rules in decision lists using Bayesian learning
著者 鶴岡, 慶雅

× 鶴岡, 慶雅

WEKO 106331

鶴岡, 慶雅

Search repository
近山, 隆

× 近山, 隆

WEKO 106332

近山, 隆

Search repository
著者別名
識別子
識別子 106333
識別子Scheme WEKO
姓名
姓名 Tsuruoka, Yoshimasa
著者別名
識別子
識別子 106334
識別子Scheme WEKO
姓名
姓名 Chikayama, Takashi
著者所属
著者所属 科学技術振興事業団
著者所属
著者所属 東京大学新領域創成科学研究科
著者所属
著者所属 Japan Science and Technology Corporation
著者所属
著者所属 School of Frontier Sciences, The University of Tokyo
抄録
内容記述タイプ Abstract
内容記述 統計的クラス分類器としての決定リストは,近年自然言語処理における様々な分野でその有効性を示している.決定リストを構成する上で最も重要な問題の一つは,ルールの信頼度の算出法である.決定リストを用いた多くの研究では,最尤推定法と簡単なスムージングにより信頼度を算出しているが,理論的な根拠に欠け推定精度も高くないという問題がある.そこで本論文では,ベイズ学習法を利用してルールの信頼度を算出する手法を示す.さらに,証拠の種類ごとに異なる事前分布を利用することで,より正確な信頼度の推定が可能になり,決定リストの性能が向上することを示す.本手法の有効性を確かめるために,語義曖昧性解消の問題に決定リストを適用して実験を行なった.英語に関してはSenseval-1 のデータを用い,日本語に関しては疑似単語を用いた.その結果,ベイズ学習による信頼度推定手法が,ルールの確率値の推定精度を高め,決定リストの分類性能を向上させることを確認した.
抄録
内容記述タイプ Abstract
内容記述 The decision list algorithm is one of the most successful algorithms for classification problems in natural language processing. The most important part of the decision list algorithm is the calculation of reliability for each rule, hence the estimation of probability for each contextual evidence. However, the majority of research efforts using decision lists do not think much of the estimation method. We propose an estimation method based on Bayesian learning which gives well-founded smoothing and better use of prior information on each type of contextual evidences. Experimental results obtained using Senseval-1 data set and Japanese pseudowords show that our method makes probability estimation more precise, leading to improvement of classification performance of the decision list algorithm.
書誌情報 自然言語処理

巻 9, 号 3, p. 3-19, 発行日 2002-04
ISSN
収録物識別子タイプ ISSN
収録物識別子 13407619
書誌レコードID
収録物識別子タイプ NCID
収録物識別子 AN10472659
フォーマット
内容記述タイプ Other
内容記述 application/pdf
日本十進分類法
主題 007
主題Scheme NDC
出版者
出版者 言語処理学会
出版者別名
The Association for Natural Language Processing
戻る
0
views
See details
Views

Versions

Ver.1 2021-03-02 00:39:29.509269
Show All versions

Share

Mendeley CiteULike Twitter Facebook Print Addthis

Cite as

Export

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by CERN Data Centre & Invenio


Powered by CERN Data Centre & Invenio