{"id":"https://openalex.org/W7095924970","doi":null,"title":"This work is supported in part by the National Science Foundation under contract 0119469.","display_name":"This work is supported in part by the National Science Foundation under contract 0119469.","publication_year":2007,"publication_date":"2007-11-21","ids":{"openalex":"https://openalex.org/W7095924970"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.7197","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ir.iit.edu/publications/./downloads/p121-ma.pdf","raw_type":"text"},"volume":null,"type":"article","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":null,"display_name":"Extracting Unstructured Data","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Extracting Unstructured Data","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ling Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036610566","display_name":"Nazli Goharian","orcid":"https://orcid.org/0000-0002-6349-5237","observed_orcids":["https://orcid.org/0000-0002-6349-5237"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nazli Goharian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65115551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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/website-templates","display_name":"web templates","score":0.9459999799728394},{"id":"https://openalex.org/keywords/unstructured-data-extraction","display_name":"unstructured data extraction","score":0.871999979019165},{"id":"https://openalex.org/keywords/search-result-precision","display_name":"search result precision","score":0.4779999852180481}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7738999724388123},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5360000133514404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4876999855041504},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48559999465942383},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.40799999237060547},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.366100013256073},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26919999718666077}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.7197","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.7197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ir.iit.edu/publications/./downloads/p121-ma.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4251360389","https://openalex.org/W108340680","https://openalex.org/W2378665865","https://openalex.org/W1560254323","https://openalex.org/W2013247697","https://openalex.org/W7098711013","https://openalex.org/W2040075907","https://openalex.org/W2399776500","https://openalex.org/W7071674855","https://openalex.org/W7096532222"],"abstract_inverted_index":{"We":[0,37],"propose":[1],"a":[2,55],"novel":[3],"approach":[4],"that":[5,33,39],"identifies":[6],"web":[7,66],"page":[8,21],"templates":[9],"and":[10,22,68],"extracts":[11],"the":[12,17,20,24,27,31,42,47,70,75],"unstructured":[13],"data.":[14],"Extracting":[15],"only":[16],"body":[18],"of":[19,44,77],"eliminating":[23],"template":[25],"increases":[26],"retrieval":[28],"precision":[29],"for":[30],"queries":[32],"generate":[34],"irrelevant":[35,45],"results.":[36],"believe":[38],"by":[40],"reducing":[41],"number":[43],"results;":[46],"users":[48],"are":[49],"encouraged":[50],"to":[51,54,58],"go":[52],"back":[53],"given":[56],"site":[57],"search.":[59],"Our":[60],"experimental":[61],"results":[62],"on":[63,69],"several":[64],"different":[65],"sites":[67],"whole":[71],"cnnfn":[72],"collection":[73],"demonstrate":[74],"feasibility":[76],"our":[78],"approach.":[79]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-27T00:00:00"}
