{"id":"https://openalex.org/W2104515","doi":null,"title":"Learning to extract information from large websites using sequential models","display_name":"Learning to extract information from large websites using sequential models","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2104515","mag":"2104515"},"language":"en","primary_location":{"id":"mag:2104515","doi":null,"is_oa":false,"landing_page_url":"http://sifaka.cs.uiuc.edu/~vgvinodv/papers/comad05.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418077","display_name":"Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Management of Data","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050525772","display_name":"V. G. Vinod Vydiswaran","orcid":"https://orcid.org/0000-0002-3122-1936","observed_orcids":["https://orcid.org/0000-0002-3122-1936"]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"V. G. Vinod Vydiswaran","raw_affiliation_strings":["Indian Inst. of Technology, Bombay"],"raw_orcid":"https://orcid.org/0000-0002-3122-1936","affiliations":[{"raw_affiliation_string":"Indian Inst. of Technology, Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616","observed_orcids":["https://orcid.org/0009-0005-9538-6616"]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["Indian Inst. of Technology, Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Inst. of Technology, Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.7214,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65845881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14435","display_name":"Information Retrieval and Data Mining","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6880000233650208},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.765999972820282},{"id":"https://openalex.org/keywords/web-graph","display_name":"web graph","score":0.4180000126361847},{"id":"https://openalex.org/keywords/focused-crawling","display_name":"focused crawling","score":0.6779999732971191},{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.37299999594688416},{"id":"https://openalex.org/keywords/computer-science-literature","display_name":"computer science literature","score":0.5979999899864197}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9039576053619385},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8872144222259521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172401189804077},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.738537073135376},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6243805289268494},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5458706617355347},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4997744560241699},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49199268221855164},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4511205852031708},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4380272626876831},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.43200254440307617},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4189903438091278},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39163973927497864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2864830195903778},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2343766987323761},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15137013792991638},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08344894647598267},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2104515","doi":null,"is_oa":false,"landing_page_url":"http://sifaka.cs.uiuc.edu/~vgvinodv/papers/comad05.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418077","display_name":"Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Management of Data","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1485536830","https://openalex.org/W1529355025","https://openalex.org/W1553019137","https://openalex.org/W1602270052","https://openalex.org/W1763978250","https://openalex.org/W1927338256","https://openalex.org/W1999138184","https://openalex.org/W1999595522","https://openalex.org/W2017726337","https://openalex.org/W2033709196","https://openalex.org/W2051434435","https://openalex.org/W2065568440","https://openalex.org/W2102667697","https://openalex.org/W2114521167","https://openalex.org/W2124673015","https://openalex.org/W2125838338","https://openalex.org/W2129874624","https://openalex.org/W2135892731","https://openalex.org/W2141099517","https://openalex.org/W2147880316","https://openalex.org/W2153072229","https://openalex.org/W2156515921"],"related_works":["https://openalex.org/W2009899513","https://openalex.org/W2464939251","https://openalex.org/W2354243931","https://openalex.org/W42631803","https://openalex.org/W91190831","https://openalex.org/W2055854503","https://openalex.org/W7096427111","https://openalex.org/W6959935033","https://openalex.org/W1553229631","https://openalex.org/W2162858242"],"abstract_inverted_index":{"We":[0,48],"propose":[1],"a":[2,20,45,53,56,67,84],"new":[3],"method":[4],"of":[5,15,42,58,78,86],"information":[6],"extraction":[7],"from":[8,35,93],"large":[9],"websites":[10],"by":[11],"learning":[12],"the":[13,25,50],"sequence":[14],"links":[16],"that":[17],"lead":[18],"to":[19,82],"specific":[21],"goal":[22],"page":[23],"on":[24,44,55],"website.":[26],"Sample":[27],"applications":[28],"include":[29],"finding":[30],"computer":[31],"science":[32],"publications":[33],"starting":[34],"university":[36],"root":[37],"pages":[38,99],"and":[39,65,90,94,97,100],"fetching":[40],"addresses":[41],"companies":[43],"web":[46],"database.":[47],"model":[49],"website":[51],"as":[52],"graph":[54],"set":[57],"important":[59],"states":[60],"chosen":[61],"via":[62],"domain":[63],"knowledge":[64],"train":[66],"Conditional":[68],"Random":[69],"Field":[70],"(CRF)":[71],"over":[72],"it.":[73],"The":[74],"conditional":[75],"exponential":[76],"models":[77],"CRFs":[79],"enable":[80],"us":[81],"exploit":[83],"variety":[85],"features":[87],"including":[88],"keywords":[89],"patterns":[91],"extracted":[92],"around":[95],"hyperlinks":[96],"HTML":[98],"any":[101],"sequential":[102],"orderings":[103],"amongst":[104],"states.":[105],"Our":[106],"technique":[107],"provides":[108],"two":[109],"times":[110],"better":[111],"harvest":[112],"rates":[113],"than":[114],"techniques":[115],"used":[116],"in":[117],"generic":[118],"focused":[119],"crawlers.":[120]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2016-06-24T00:00:00"}