{"id":"https://openalex.org/W4412877105","doi":"https://doi.org/10.1145/3711896.3737207","title":"Cross-Domain Web Information Extraction at Pinterest","display_name":"Cross-Domain Web Information Extraction at Pinterest","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877105","doi":"https://doi.org/10.1145/3711896.3737207"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057988285","display_name":"Michael Farag","orcid":"https://orcid.org/0000-0002-6474-1911"},"institutions":[{"id":"https://openalex.org/I4210111593","display_name":"Bridgepoint Active Healthcare","ror":"https://ror.org/01zeqwe54","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210111593","https://openalex.org/I4210130843"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Michael Farag","raw_affiliation_strings":["Pinterest, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Pinterest, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210111593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175150","display_name":"Patrick Halina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111593","display_name":"Bridgepoint Active Healthcare","ror":"https://ror.org/01zeqwe54","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210111593","https://openalex.org/I4210130843"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Halina","raw_affiliation_strings":["Pinterest, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Pinterest, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210111593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175151","display_name":"Andrey Zaytsev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrey Zaytsev","raw_affiliation_strings":["Pinterest, San Francisco, California, USA"],"affiliations":[{"raw_affiliation_string":"Pinterest, San Francisco, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175152","display_name":"Alekhya Munagala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111593","display_name":"Bridgepoint Active Healthcare","ror":"https://ror.org/01zeqwe54","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210111593","https://openalex.org/I4210130843"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alekhya Munagala","raw_affiliation_strings":["Pinterest, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Pinterest, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210111593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003062388","display_name":"Imtihan Ahmed","orcid":"https://orcid.org/0000-0003-1045-5458"},"institutions":[{"id":"https://openalex.org/I4210111593","display_name":"Bridgepoint Active Healthcare","ror":"https://ror.org/01zeqwe54","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210111593","https://openalex.org/I4210130843"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Imtihan Ahmed","raw_affiliation_strings":["Pinterest, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Pinterest, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210111593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115695179","display_name":"Junhao Wang","orcid":"https://orcid.org/0000-0001-7357-429X"},"institutions":[{"id":"https://openalex.org/I4210111593","display_name":"Bridgepoint Active Healthcare","ror":"https://ror.org/01zeqwe54","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I4210111593","https://openalex.org/I4210130843"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Junhao Wang","raw_affiliation_strings":["Pinterest, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Pinterest, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210111593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057988285"],"corresponding_institution_ids":["https://openalex.org/I4210111593"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28371158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4406","last_page":"4413"},"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/T13976","display_name":"Web visibility and informetrics","score":0.942799985408783,"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/T11478","display_name":"Caching and Content Delivery","score":0.9300000071525574,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7595334649085999},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5529744625091553},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5503432750701904},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5142382979393005},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4830673038959503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595334649085999},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5529744625091553},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5503432750701904},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5142382979393005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4830673038959503},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711896.3737207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01096","pdf_url":"https://arxiv.org/pdf/2508.01096","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2508.01096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01096","pdf_url":"https://arxiv.org/pdf/2508.01096","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2024091454","https://openalex.org/W2135479443","https://openalex.org/W2148317291","https://openalex.org/W2394650700","https://openalex.org/W2573020254","https://openalex.org/W3207107805","https://openalex.org/W4290877962","https://openalex.org/W4291127187","https://openalex.org/W4304013646","https://openalex.org/W4385568029","https://openalex.org/W4393154852","https://openalex.org/W6711702419"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"internet":[1],"offers":[2],"a":[3,11,18,61,67,79,137],"massive":[4],"repository":[5],"of":[6],"unstructured":[7],"information,":[8],"but":[9],"it's":[10],"significant":[12],"challenge":[13],"to":[14,25,36,115],"convert":[15],"this":[16,45,105],"into":[17,78],"structured":[19,28],"format.":[20],"At":[21],"Pinterest,":[22],"the":[23,156],"ability":[24],"accurately":[26,119],"extract":[27,116],"product":[29],"data":[30],"from":[31],"e-commerce":[32],"websites":[33],"is":[34,140],"essential":[35],"enhance":[37],"user":[38],"experiences":[39],"and":[40,58,75,99],"improve":[41],"content":[42],"distribution.":[43],"In":[44],"paper,":[46],"we":[47],"present":[48],"Pinterest's":[49],"system":[50,138],"for":[51,84],"attribute":[52],"extraction,":[53],"which":[54],"achieves":[55],"remarkable":[56],"accuracy":[57],"scalability":[59],"at":[60],"manageable":[62],"cost.":[63],"Our":[64,134],"approach":[65],"leverages":[66],"novel":[68],"webpage":[69],"representation":[70,89],"that":[71,139],"combines":[72],"structural,":[73],"visual,":[74],"text":[76],"modalities":[77],"compact":[80],"form,":[81],"optimizing":[82],"it":[83],"small":[85],"model":[86],"learning.":[87],"This":[88],"captures":[90],"each":[91],"visible":[92],"HTML":[93],"node":[94],"with":[95],"its":[96],"text,":[97],"style":[98],"layout":[100],"information.":[101],"We":[102],"show":[103],"how":[104],"allows":[106],"simple":[107],"models":[108],"such":[109,128],"as":[110,129],"eXtreme":[111],"Gradient":[112],"Boosting":[113],"(XGBoost)":[114],"attributes":[117],"more":[118,122,153],"than":[120,155],"much":[121],"complex":[123],"Large":[124],"Language":[125],"Models":[126],"(LLMs)":[127],"Generative":[130],"Pre-trained":[131],"Transformer":[132],"(GPT).":[133],"results":[135],"demonstrate":[136],"highly":[141],"scalable,":[142],"processing":[143],"over":[144],"1,000":[145],"URLs":[146],"per":[147],"second,":[148],"while":[149],"being":[150],"1000":[151],"times":[152],"cost-effective":[154],"cheapest":[157],"GPT":[158],"alternatives.":[159]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
