{"id":"https://openalex.org/W4206502674","doi":"https://doi.org/10.1145/3493700.3493713","title":"Extraction of Product Specifications from the Web - Going Beyond Tables and Lists","display_name":"Extraction of Product Specifications from the Web - Going Beyond Tables and Lists","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4206502674","doi":"https://doi.org/10.1145/3493700.3493713"},"language":"en","primary_location":{"id":"doi:10.1145/3493700.3493713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science &amp; Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.02896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091520551","display_name":"Govind Krishnan Gangadhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Govind Krishnan Gangadhar","raw_affiliation_strings":["Clustr, IN"],"affiliations":[{"raw_affiliation_string":"Clustr, IN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018328252","display_name":"Ashish Kulkarni","orcid":"https://orcid.org/0000-0002-7734-4368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Kulkarni","raw_affiliation_strings":["Clustr, IN"],"affiliations":[{"raw_affiliation_string":"Clustr, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091520551"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3183,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57447725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"27"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9884999990463257,"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/T11719","display_name":"Data Quality and Management","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8202195167541504},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5118033289909363},{"id":"https://openalex.org/keywords/product-design-specification","display_name":"Product design specification","score":0.49369534850120544},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.47323521971702576},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.44701117277145386},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36712002754211426},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35936108231544495},{"id":"https://openalex.org/keywords/product-design","display_name":"Product design","score":0.35847634077072144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19561359286308289},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07727766036987305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202195167541504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5118033289909363},{"id":"https://openalex.org/C45135082","wikidata":"https://www.wikidata.org/wiki/Q16960030","display_name":"Product design specification","level":4,"score":0.49369534850120544},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.47323521971702576},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.44701117277145386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36712002754211426},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35936108231544495},{"id":"https://openalex.org/C120823896","wikidata":"https://www.wikidata.org/wiki/Q1043226","display_name":"Product design","level":3,"score":0.35847634077072144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19561359286308289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07727766036987305},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3493700.3493713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science &amp; Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.02896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.02896","pdf_url":"https://arxiv.org/pdf/2201.02896","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.02896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.02896","pdf_url":"https://arxiv.org/pdf/2201.02896","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1522301498","https://openalex.org/W1553019137","https://openalex.org/W1614298861","https://openalex.org/W2001793573","https://openalex.org/W2024105308","https://openalex.org/W2045968013","https://openalex.org/W2078206655","https://openalex.org/W2080132606","https://openalex.org/W2102189859","https://openalex.org/W2102288093","https://openalex.org/W2104086170","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2140602286","https://openalex.org/W2149364369","https://openalex.org/W2296045323","https://openalex.org/W2398207884","https://openalex.org/W2604225376","https://openalex.org/W2745153524","https://openalex.org/W2899418290","https://openalex.org/W2908018635","https://openalex.org/W2945748862","https://openalex.org/W3034300118","https://openalex.org/W3162817740"],"related_works":["https://openalex.org/W2158482288","https://openalex.org/W1567498295","https://openalex.org/W2031767561","https://openalex.org/W4251323751","https://openalex.org/W4285600477","https://openalex.org/W2394433794","https://openalex.org/W2161832433","https://openalex.org/W2783593393","https://openalex.org/W2898204433","https://openalex.org/W2088313277"],"abstract_inverted_index":{"E-commerce":[0],"product":[1,8,18,25,74,98,141,147,166,180,206],"pages":[2],"on":[3,72,139],"the":[4,67,111,136,146,185,192],"web":[5],"often":[6],"present":[7,96],"specification":[9,99,118,137,172,194,207],"data":[10],"in":[11],"structured":[12],"tabular":[13],"blocks.":[14,119],"Extraction":[15],"of":[16,42,66,123,165,178,187],"these":[17,56,151],"attribute-value":[19,148],"specifications":[20,75,167],"has":[21,70],"benefited":[22],"applications":[23],"like":[24],"catalogue":[26],"curation,":[27],"search,":[28],"question":[29],"answering,":[30],"and":[31,78,108,126,130,197],"others.":[32],"However,":[33],"across":[34,110],"different":[35,179],"Websites,":[36],"there":[37],"is":[38],"a":[39,63,88,97,121,140,162,176],"wide":[40],"variety":[41],"HTML":[43,113],"elements":[44,114],"(like":[45],"<table>,":[46],"<ul>,":[47],"<div>,":[48],"<span>,":[49],"<dl>,":[50],"etc.)":[51],"typically":[52],"used":[53,115],"to":[54,87,191,204],"render":[55],"blocks":[57,138,152,173],"that":[58,102],"makes":[59],"their":[60],"automatic":[61],"extraction":[62,90,100,195],"challenge.":[64],"Most":[65],"current":[68,193],"research":[69],"focused":[71],"extracting":[73],"from":[76,83,150,169,175],"tables":[77,105],"lists":[79,107],"and,":[80],"therefore,":[81],"suffers":[82],"recall":[84],"when":[85],"applied":[86],"large-scale":[89,205],"setting.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95,133],"approach":[101,155,189],"goes":[103],"beyond":[104],"or":[106],"generalizes":[109],"diverse":[112,171],"for":[116],"rendering":[117],"Using":[120],"combination":[122],"hand-coded":[124],"features":[125],"deep":[127],"learned":[128],"spatial":[129],"token":[131],"features,":[132],"first":[134],"identify":[135],"page.":[142],"We":[143,160],"then":[144],"extract":[145],"pairs":[149],"following":[153],"an":[154],"inspired":[156],"by":[157],"wrapper":[158],"induction.":[159],"created":[161],"labeled":[163],"dataset":[164],"extracted":[168],"14,111":[170],"taken":[174],"range":[177],"websites.":[181],"Our":[182],"experiments":[183],"show":[184],"efficacy":[186],"our":[188,199],"compared":[190],"models":[196],"support":[198],"claim":[200],"about":[201],"its":[202],"application":[203],"extraction.":[208]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}