{"id":"https://openalex.org/W4384648987","doi":"https://doi.org/10.1145/3539618.3591846","title":"KATIE: A System for Key Attributes Identification in Product Knowledge Graph Construction","display_name":"KATIE: A System for Key Attributes Identification in Product Knowledge Graph Construction","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384648987","doi":"https://doi.org/10.1145/3539618.3591846"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591846","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591846","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591846","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063675425","display_name":"Btissam Er-Rahmadi","orcid":"https://orcid.org/0000-0003-0526-661X"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Btissam Er-Rahmadi","raw_affiliation_strings":["Huawei Technologies R&D UK, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0526-661X","affiliations":[{"raw_affiliation_string":"Huawei Technologies R&D UK, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010343739","display_name":"Arturo Oncevay","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arturo Oncevay","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7675-6208","affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050120073","display_name":"Yuanyi Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuanyi Ji","raw_affiliation_strings":["Huawei Technologies R&D UK, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0004-9700-9438","affiliations":[{"raw_affiliation_string":"Huawei Technologies R&D UK, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066422711","display_name":"Jeff Z. Pan","orcid":"https://orcid.org/0000-0002-9779-2088"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeff Z. Pan","raw_affiliation_strings":["Huawei Technologies R&D UK & The University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-9779-2088","affiliations":[{"raw_affiliation_string":"Huawei Technologies R&D UK & The University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I4210160618","https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063675425"],"corresponding_institution_ids":["https://openalex.org/I4210160618"],"apc_list":null,"apc_paid":null,"fwci":0.3408,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64619706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3320","last_page":"3324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9926999807357788,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9926999807357788,"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":0.9857000112533569,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.775374174118042},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.683577299118042},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6609055995941162},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6274932622909546},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.578885555267334},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5548765659332275},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5246720314025879},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.519131600856781},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4785914421081543},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.46000367403030396},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45725977420806885},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40032505989074707},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3651283383369446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24391144514083862},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.185854971408844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11462116241455078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775374174118042},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.683577299118042},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6609055995941162},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6274932622909546},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.578885555267334},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5548765659332275},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5246720314025879},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.519131600856781},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4785914421081543},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.46000367403030396},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45725977420806885},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40032505989074707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3651283383369446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24391144514083862},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.185854971408844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11462116241455078},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591846","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591846","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3539618.3591846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3591846","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3591846","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384648987.pdf","grobid_xml":"https://content.openalex.org/works/W4384648987.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W203440368","https://openalex.org/W2584261443","https://openalex.org/W2883780523","https://openalex.org/W2897797793","https://openalex.org/W2952286769","https://openalex.org/W2978017171","https://openalex.org/W2986213397","https://openalex.org/W2990816204","https://openalex.org/W3032187523","https://openalex.org/W3037151198","https://openalex.org/W3087991689","https://openalex.org/W3098003395","https://openalex.org/W3100825476","https://openalex.org/W3101157305","https://openalex.org/W3168857653","https://openalex.org/W4205677783","https://openalex.org/W4253203888","https://openalex.org/W4306317063","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W3095158916","https://openalex.org/W1984733048","https://openalex.org/W38260586","https://openalex.org/W1730245467","https://openalex.org/W52394763","https://openalex.org/W50774052","https://openalex.org/W2592441986","https://openalex.org/W2051135816","https://openalex.org/W4244960141","https://openalex.org/W2017955920"],"abstract_inverted_index":{"We":[0,13,77,105,135],"present":[1],"part":[2],"of":[3,28,99,131,147],"Huawei's":[4],"efforts":[5],"in":[6,26],"building":[7],"a":[8,65,79,103,145],"Product":[9],"Knowledge":[10],"Graph":[11],"(PKG).":[12],"want":[14],"to":[15,31,72,93,102,116,140,160],"identify":[16],"which":[17,61],"product":[18,32,50],"attributes":[19,42,119,150],"(i.e.":[20,34],"properties)":[21],"are":[22,46],"relevant":[23],"and":[24,43,68,97,144],"important":[25],"terms":[27],"shopping":[29],"decisions":[30],"categories":[33,142],"classes).":[35],"This":[36],"is":[37],"particularly":[38],"challenging":[39],"when":[40],"the":[41,74,95,129,161],"their":[44,124,132],"values":[45,133],"mined":[47,149],"from":[48,151],"online":[49],"catalogues,":[51],"i.e.":[52],"HTML":[53],"pages.":[54,153],"These":[55],"web":[56,152],"pages":[57],"contain":[58],"semi-structured":[59],"data,":[60],"do":[62],"not":[63,122],"follow":[64],"concerted":[66],"format":[67],"use":[69],"diverse":[70],"vocabulary":[71],"designate":[73],"same":[75],"features.":[76],"propose":[78,107],"system":[80],"for":[81],"key":[82],"attribute":[83,101,109],"identification":[84,111],"(KATIE)":[85],"based":[86],"on":[87],"fine-tuning":[88],"pre-trained":[89],"models":[90],"(e.g.,":[91],"DistilBERT)":[92],"predict":[94],"applicability":[96],"importance":[98],"an":[100,108],"category.":[104],"also":[106,128],"synonyms":[110],"module":[112],"that":[113],"allows":[114],"us":[115],"discover":[117],"synonymous":[118],"by":[120],"considering":[121],"only":[123],"labels'":[125],"similarities":[126],"but":[127],"similarity":[130],"sets.":[134],"have":[136],"evaluated":[137],"our":[138],"approach":[139],"Huawei":[141],"taxonomy":[143],"set":[146],"internally":[148],"KATIE":[154],"guarantees":[155],"promising":[156],"performance":[157],"results":[158],"compared":[159],"most":[162],"recent":[163],"baselines.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}