WEKO3
アイテム
{"_buckets": {"deposit": "d8256f7e-dd1c-4015-a9ba-5ad25a9fdb64"}, "_deposit": {"created_by": 3, "id": "28861", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "28861"}, "status": "published"}, "_oai": {"id": "oai:waseda.repo.nii.ac.jp:00028861", "sets": ["2080"]}, "author_link": ["50016", "50015", "50014"], "item_10003_biblio_info_90": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2005-11-16", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "114", "bibliographicPageStart": "105", "bibliographic_titles": [{}]}]}, "item_10003_creator_87": {"attribute_name": "著者別名", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Shimazu, Akira"}], "nameIdentifiers": [{"nameIdentifier": "50016", "nameIdentifierScheme": "WEKO"}]}]}, "item_10003_description_123": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"subitem_description": "text", "subitem_description_type": "Other"}]}, "item_10003_description_88": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Word Sense Disambiguation (WSD) is the task of choosing the right sense of an ambiguous word given a context. Using Naive Bayesian (NB) classifiers is known as one of the best methods for supervised approaches for WSD (Mooney, 1996; Pedersen, 2000), and this model usually uses only a topic context represented by unordered words in a large context. In this paper, we show that by adding more rich knowledge, represented by ordered words in a local context and collocations, the NB classifier can achieve higher accuracy in comparison with the best previously published results. The features were chosen using a forward sequential selection algorithm. Our experiments obtained 92.3% accuracy for four common test words (interest, line, hard, serve). We also tested on a large dataset, the DSO corpus, and obtained accuracies of 66.4% for verbs and 72.7% for nouns.", "subitem_description_type": "Abstract"}]}, "item_10003_publisher_116": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Logico-Linguistic Society of Japan"}]}, "item_10003_relation_124": {"attribute_name": "シリーズ", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "Oral Session"}]}]}, "item_10003_relation_125": {"attribute_name": "関係URI", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "http://www.decode.waseda.ac.jp/PACLIC18/"}]}]}, "item_10003_subject_100": {"attribute_name": "日本十進分類法", "attribute_value_mlt": [{"subitem_subject": "801.06", "subitem_subject_scheme": "NDC"}]}, "item_10003_subject_110": {"attribute_name": "米国議会図書館件名標目", "attribute_value_mlt": [{"subitem_subject": "Computational linguistics--Congresses", "subitem_subject_scheme": "LCSH"}]}, "item_10003_text_144": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_text_value": "http://hdl.handle.net/2065/564"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Le, Cuong Anh"}], "nameIdentifiers": [{"nameIdentifier": "50014", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "島津, 明"}], "nameIdentifiers": [{"nameIdentifier": "50015", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2016-11-28"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "oral-8.pdf", "filesize": [{"value": "484.0 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 484000.0, "url": {"label": "oral-8.pdf", "url": "https://waseda.repo.nii.ac.jp/record/28861/files/oral-8.pdf"}, "version_id": "3885a7bc-6a49-4a32-80d9-1703427dfd40"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "High WSD Accuracy Using Naive Bayesian Classifier with Rich Features", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "High WSD Accuracy Using Naive Bayesian Classifier with Rich Features", "subitem_title_language": "en"}]}, "item_type_id": "10003", "owner": "3", "path": ["2080"], "permalink_uri": "http://hdl.handle.net/2065/564", "pubdate": {"attribute_name": "公開日", "attribute_value": "2008-04-28"}, "publish_date": "2008-04-28", "publish_status": "0", "recid": "28861", "relation": {}, "relation_version_is_last": true, "title": ["High WSD Accuracy Using Naive Bayesian Classifier with Rich Features"], "weko_shared_id": -1}
High WSD Accuracy Using Naive Bayesian Classifier with Rich Features
http://hdl.handle.net/2065/564
http://hdl.handle.net/2065/5643287872a-1202-415e-959d-71899a56eee1
名前 / ファイル | ライセンス | アクション |
---|---|---|
oral-8.pdf (484.0 kB)
|
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2008-04-28 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | High WSD Accuracy Using Naive Bayesian Classifier with Rich Features | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
資源タイプ | conference paper | |||||
著者 |
Le, Cuong Anh
× Le, Cuong Anh× 島津, 明 |
|||||
著者別名 |
Shimazu, Akira
× Shimazu, Akira |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Word Sense Disambiguation (WSD) is the task of choosing the right sense of an ambiguous word given a context. Using Naive Bayesian (NB) classifiers is known as one of the best methods for supervised approaches for WSD (Mooney, 1996; Pedersen, 2000), and this model usually uses only a topic context represented by unordered words in a large context. In this paper, we show that by adding more rich knowledge, represented by ordered words in a local context and collocations, the NB classifier can achieve higher accuracy in comparison with the best previously published results. The features were chosen using a forward sequential selection algorithm. Our experiments obtained 92.3% accuracy for four common test words (interest, line, hard, serve). We also tested on a large dataset, the DSO corpus, and obtained accuracies of 66.4% for verbs and 72.7% for nouns. | |||||
書誌情報 | p. 105-114, 発行日 2005-11-16 | |||||
件名 | ||||||
主題Scheme | NDC | |||||
主題 | 801.06 | |||||
件名 | ||||||
主題Scheme | LCSH | |||||
主題 | Computational linguistics--Congresses | |||||
出版者 | ||||||
出版者 | Logico-Linguistic Society of Japan | |||||
データタイプ | ||||||
内容記述タイプ | Other | |||||
内容記述 | text | |||||
HDL URI | ||||||
http://hdl.handle.net/2065/564 |