{"_buckets": {"deposit": "84125f4a-79f2-4f55-9cd0-4b2dabd1cd50"}, "_deposit": {"id": "4522", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "4522"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/4522", "sets": ["user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Extracting Information Content from Web Pages Using Block Clustering Method", "subitem_1551255648112": "en_US"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "The World Wide Web is the main “allkind of information” repository and has been sofar very successful in disseminating to humans.As web sites are getting more complicated, theconstruction of web information extractionsystems becomes more difficult and timeconsuming. Therefore we need to mine the maincontent of web page in order to extractinformation from such web pages. In this paper,we study the problem of automaticallyextracting the web information (unsupervisedIE) without any learning examples or othersimilar human input. Firstly, web pages aresegment into several raw chunks. Then removethe noisy blocks based on product features.Data region identification is based on theobservation that appearance similarity of thedata record in web document. Therefore blockclustering method is proposed based on thisobservation. This approach requires no humanintervention and experimental results haveshown its accuracy to be promising."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Information Extraction (IE)"}, {"interim": "Wrapper"}, {"interim": "Document Object Model (DOM)"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2019-11-15"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "10103.pdf", "filesize": [{"value": "463 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 463000.0, "url": {"url": "https://meral.edu.mm/record/4522/files/10103.pdf"}, "version_id": "ddbffd17-b905-4ab5-a2e7-4367de367f31"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "Tenth International Conference On Computer Applications (ICCA 2012)", "subitem_pages": "", "subitem_volume": ""}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "", "subitem_c_date": "", "subitem_conference_title": "", "subitem_part": "", "subitem_place": "", "subitem_session": "", "subitem_website": ""}]}, "item_1583103211336": {"attribute_name": "Books/reports/chapters", "attribute_value_mlt": [{"subitem_book_title": "", "subitem_isbn": "", "subitem_pages": "", "subitem_place": "", "subitem_publisher": ""}]}, "item_1583103233624": {"attribute_name": "Thesis/dissertations", "attribute_value_mlt": [{"subitem_awarding_university": "", "subitem_supervisor(s)": [{"subitem_supervisor": ""}]}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Hlaing, Nwe Nwe"}, {"subitem_authors_fullname": "Nyunt, Thi Thi Soe"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2012-02-28"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/2447"}, "item_title": "Extracting Information Content from Web Pages Using Block Clustering Method", "item_type_id": "21", "owner": "1", "path": ["1597824273898"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000004522", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-11-15"}, "publish_date": "2019-11-15", "publish_status": "0", "recid": "4522", "relation": {}, "relation_version_is_last": true, "title": ["Extracting Information Content from Web Pages Using Block Clustering Method"], "weko_shared_id": -1}