{"id":"https://openalex.org/W2009899513","doi":"https://doi.org/10.1145/1046456.1046464","title":"Learning to extract information from large domain-specific websites using sequential models","display_name":"Learning to extract information from large domain-specific websites using sequential models","publication_year":2004,"publication_date":"2004-12-01","ids":{"openalex":"https://openalex.org/W2009899513","doi":"https://doi.org/10.1145/1046456.1046464","mag":"2009899513"},"language":"en","primary_location":{"id":"doi:10.1145/1046456.1046464","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1046456.1046464","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5031035935","display_name":"Sunita Sarawagi","orcid":"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":true,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["","Indian Inst. of Technology, Bombay"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Indian Inst. of Technology, Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050525772","display_name":"V. G. Vinod Vydiswaran","orcid":"https://orcid.org/0000-0002-3122-1936"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V. G. Vinod Vydiswaran","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031035935"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.4497,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74188599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":"2","first_page":"61","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8851423263549805},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.7263752222061157},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7019058465957642},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5455822348594666},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5329694747924805},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5116227269172668},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5104052424430847},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5090712904930115},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5078616738319397},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5008838176727295},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4781568944454193},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4739903509616852},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46540194749832153},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4499165713787079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4361268877983093},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.41130390763282776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3396455645561218},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.28281068801879883},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.251278817653656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8851423263549805},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.7263752222061157},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7019058465957642},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5455822348594666},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5329694747924805},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5116227269172668},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5104052424430847},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5090712904930115},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5078616738319397},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5008838176727295},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4781568944454193},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4739903509616852},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46540194749832153},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4499165713787079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361268877983093},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.41130390763282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3396455645561218},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28281068801879883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.251278817653656},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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":"doi:10.1145/1046456.1046464","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1046456.1046464","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2104515","https://openalex.org/W1485536830","https://openalex.org/W1999138184","https://openalex.org/W2017726337","https://openalex.org/W2033709196","https://openalex.org/W2051434435","https://openalex.org/W2102667697","https://openalex.org/W2124673015","https://openalex.org/W2125838338","https://openalex.org/W2141099517","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2714497087"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W50079190","https://openalex.org/W182104056","https://openalex.org/W2011251309","https://openalex.org/W2511246383","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2184553228","https://openalex.org/W1492005981"],"abstract_inverted_index":{"In":[0],"this":[1,59],"article":[2],"we":[3],"describe":[4],"a":[5,44,61,77,107],"novel":[6],"information":[7],"extraction":[8],"task":[9,28,45],"on":[10,36,128],"the":[11,22,124],"web":[12,129],"and":[13,84,88,91,100],"show":[14],"how":[15],"it":[16],"can":[17],"be":[18],"solved":[19,65],"effectively":[20],"using":[21,66],"emerging":[23],"conditional":[24],"exponential":[25],"models.":[26],"The":[27],"involves":[29],"learning":[30],"to":[31,47,75],"find":[32,48],"specific":[33],"goal":[34],"pages":[35],"large":[37],"domain-specific":[38],"websites.":[39],"An":[40],"example":[41],"of":[42,80,97,103,126],"such":[43],"is":[46,112],"computer":[49],"science":[50],"publications":[51],"starting":[52],"from":[53,87],"university":[54],"root":[55],"pages.":[56],"We":[57],"encode":[58],"as":[60],"sequential":[62],"labeling":[63],"problem":[64],"Conditional":[67],"Random":[68],"Fields":[69],"(CRFs).":[70],"These":[71],"models":[72,121],"enable":[73],"us":[74],"exploit":[76],"wide":[78],"variety":[79],"features":[81],"including":[82],"keywords":[83],"patterns":[85],"extracted":[86],"around":[89],"hyperlinks":[90],"HTML":[92],"pages,":[93,99],"dependency":[94],"among":[95],"labels":[96],"adjacent":[98],"existing":[101],"databases":[102],"named":[104],"entities":[105],"in":[106],"unified":[108],"probabilistic":[109],"framework.":[110],"This":[111],"an":[113],"important":[114],"advantage":[115],"over":[116],"previous":[117],"rule-based":[118],"or":[119],"generative":[120],"for":[122],"tackling":[123],"challenges":[125],"diversity":[127],"data.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}