{"id":"https://openalex.org/W168525779","doi":null,"title":"A structured wrapper induction system for extracting information from semi-structured documents","display_name":"A structured wrapper induction system for extracting information from semi-structured documents","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W168525779","mag":"168525779"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.8768","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.8768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.smi.ucd.ie/ATEM2001/proceedings/cohen-atem2001.ps.gz","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":"https://openalex.org/A5051617344","display_name":"William W. Cohen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"William W. Cohen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051617344"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.5449,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98447144,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0,"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/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/wrapper-induction","display_name":"wrapper induction","score":0.9409999847412109},{"id":"https://openalex.org/keywords/semi-structured-documents","display_name":"semi-structured documents","score":0.843999981880188},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.859000027179718},{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.593999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247992753982544},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5234426856040955},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.4209989309310913},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33066684007644653},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12491631507873535},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.8768","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.8768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.smi.ucd.ie/ATEM2001/proceedings/cohen-atem2001.ps.gz","raw_type":"text"},{"id":"mag:168525779","doi":null,"is_oa":false,"landing_page_url":"http://ci.nii.ac.jp/naid/10014940013/en/","pdf_url":null,"source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","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":"International Joint Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W109947125","https://openalex.org/W200042785","https://openalex.org/W1514468887","https://openalex.org/W1531743498","https://openalex.org/W1563062065","https://openalex.org/W1987902506","https://openalex.org/W1999138184","https://openalex.org/W2039683780","https://openalex.org/W2111221376","https://openalex.org/W2135479443","https://openalex.org/W2154297071","https://openalex.org/W2154763111","https://openalex.org/W2169318468"],"related_works":["https://openalex.org/W7100972066","https://openalex.org/W2153072229","https://openalex.org/W4391872","https://openalex.org/W200042785","https://openalex.org/W7095742974","https://openalex.org/W1553019137","https://openalex.org/W7095313331","https://openalex.org/W2080132606","https://openalex.org/W7099379162","https://openalex.org/W7100038713"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,27,97],"extensible":[3],"architecture":[4,17],"which":[5,73,101],"allows":[6],"wrapper-learning":[7,22,99],"systems":[8],"to":[9,49,105],"be":[10,62],"easily":[11],"constructed":[12,63],"and":[13,93],"tuned.":[14],"In":[15],"this":[16],"the":[18,21,75,80],"bias":[19],"of":[20,30,54,79,83,96],"system":[23,87,100],"is":[24,46,90,94],"encoded":[25],"as":[26],"ordered":[28],"set":[29,53],"\"builders\",":[31],"each":[32],"associated":[33],"with":[34],"some":[35],"restricted":[36],"extraction":[37],"language":[38],"L.":[39,58],"To":[40],"implement":[41,50],"a":[42,51],"new":[43],"builder":[44],"it":[45],"only":[47],"necessary":[48],"small":[52],"core":[55],"operations":[56],"for":[57],"Builders":[59],"can":[60],"also":[61],"by":[64],"combining":[65],"other":[66],"builders.":[67],"A":[68],"single":[69],"master":[70],"learning":[71,86],"algorithm":[72],"invokes":[74],"builders":[76],"handles":[77],"most":[78],"real":[81],"work":[82],"learning.":[84],"The":[85],"described":[88],"here":[89],"fully":[91],"implemented,":[92],"part":[95],"\"industrial-strength\"":[98],"has":[102],"been":[103],"used":[104],"extract":[106],"job":[107],"postings":[108],"from":[109],"more":[110],"than":[111],"500":[112],"sites.":[113],"1":[114]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2016-06-24T00:00:00"}