{"id":"https://openalex.org/W4391095317","doi":"https://doi.org/10.1109/bigdata59044.2023.10386079","title":"SST: Semantic and Structural Transformers for Hierarchy-aware Language Models in E-commerce","display_name":"SST: Semantic and Structural Transformers for Hierarchy-aware Language Models in E-commerce","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391095317","doi":"https://doi.org/10.1109/bigdata59044.2023.10386079"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386079","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5040617244","display_name":"Karan Samel","orcid":"https://orcid.org/0009-0002-8788-5624"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Samel","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025250287","display_name":"Houyu Zhang","orcid":"https://orcid.org/0000-0003-0360-6035"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Houyu Zhang","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643102","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0003-4679-9500"},"institutions":[{"id":"https://openalex.org/I3007373383","display_name":"Walgreens (United States)","ror":"https://ror.org/00615jn62","country_code":"US","type":"company","lineage":["https://openalex.org/I3007373383"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Walgreens AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Walgreens AI Lab","institution_ids":["https://openalex.org/I3007373383"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030361161","display_name":"Haoming Jiang","orcid":"https://orcid.org/0000-0003-0789-525X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Jiang","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102748671","display_name":"Ping Qing","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Ping","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048356362","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0002-0439-5199"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":["University of Washington,Amazon","Amazon, University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Amazon","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I201448701"]},{"raw_affiliation_string":"Amazon, University of Washington","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018343158","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0003-2126-6054"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082750097","display_name":"Belinda Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Belinda Zeng","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013670321","display_name":"Trishul Chilimbi","orcid":"https://orcid.org/0000-0001-6711-1117"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trishul Chilimbi","raw_affiliation_strings":["Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"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":0.19223874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"838","last_page":"846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916626930236816},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5229952335357666},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5072550177574158},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43610039353370667},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32924386858940125},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06459233164787292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916626930236816},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5229952335357666},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5072550177574158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43610039353370667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32924386858940125},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06459233164787292},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386079","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2013296003","https://openalex.org/W2034927834","https://openalex.org/W2053811285","https://openalex.org/W2130942839","https://openalex.org/W2141880913","https://openalex.org/W2150102617","https://openalex.org/W2251644777","https://openalex.org/W2293569829","https://openalex.org/W2295623143","https://openalex.org/W2604314403","https://openalex.org/W2759474451","https://openalex.org/W2885625746","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2920292591","https://openalex.org/W2938830017","https://openalex.org/W2953356739","https://openalex.org/W2962910668","https://openalex.org/W2964347323","https://openalex.org/W2965373594","https://openalex.org/W2965839155","https://openalex.org/W2970986510","https://openalex.org/W2996428491","https://openalex.org/W2998385486","https://openalex.org/W3035690777","https://openalex.org/W3104770333","https://openalex.org/W3151929433","https://openalex.org/W3158986179","https://openalex.org/W3176676637","https://openalex.org/W3182414949","https://openalex.org/W3211394146","https://openalex.org/W4221151676","https://openalex.org/W4294589293","https://openalex.org/W4297733535","https://openalex.org/W4298094466","https://openalex.org/W4385245566","https://openalex.org/W4385567242","https://openalex.org/W4385572768","https://openalex.org/W6679436768","https://openalex.org/W6681875376","https://openalex.org/W6697461476","https://openalex.org/W6719382505","https://openalex.org/W6730615220","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6761910064","https://openalex.org/W6766012997","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6795224213","https://openalex.org/W6798398338","https://openalex.org/W6804049574"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2365264209","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W962203960","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Hierarchies":[0],"are":[1,160],"common":[2],"structures":[3],"used":[4,135],"to":[5,22,28,49,69,90,139,179,213],"organize":[6],"data,":[7],"such":[8,221],"as":[9],"e-commerce":[10,37,185,230],"hierarchies":[11,42],"associated":[12],"with":[13,174],"product":[14,18,25,97,126],"data.":[15],"With":[16,162],"these":[17,66],"hierarchies,":[19],"we":[20,85,165],"aim":[21],"learn":[23],"hierarchy-aware":[24,157],"text":[26,47,63,98,127,158],"embeddings":[27,48,52,159],"improve":[29],"fine-tuning":[30,75,172,180],"performance":[31,181],"on":[32,76,183],"a":[33,61,87,103,129],"variety":[34],"of":[35,105,169],"downstream":[36,186],"tasks.":[38],"Existing":[39],"methods":[40],"leverage":[41,102],"by":[43,54,136,218],"either":[44],"aligning":[45,55],"the":[46,56,93,96,106,121,125,137,141,145,152,167,189,229],"separate":[50],"hierarchical":[51,57],"or":[53],"information":[58],"implicitly":[59,91],"within":[60,95],"unified":[62],"Transformer.":[64],"Although":[65],"models":[67,212],"optimize":[68],"predict":[70],"hierarchy":[71,94,192,196],"information,":[72],"performing":[73],"further":[74],"new":[77],"tasks":[78,187],"is":[79,112,133,148,205],"non-trivial.":[80],"To":[81],"bridge":[82],"this":[83,163,203],"gap,":[84],"propose":[86],"pre-training":[88,107],"architecture":[89],"encode":[92],"and":[99,116],"then":[100,134],"directly":[101],"sub-set":[104],"model":[108],"during":[109,200],"fine-tuning.":[110,201,215],"Pre-training":[111],"done":[113,149],"through":[114],"Semantic":[115],"Structural":[117],"Transformers":[118],"(SST)":[119],"where":[120],"Semantic-Transformer":[122],"first":[123],"encodes":[124],"into":[128],"contextual":[130],"embedding,":[131],"which":[132],"Structural-Transformer":[138],"infer":[140],"product\u2019s":[142],"path":[143],"in":[144],"hierarchy.":[146],"Fine-tuning":[147],"using":[150],"only":[151],"initial":[153],"Semantic-Transformer,":[154],"now":[155],"that":[156],"learned.":[161],"design,":[164],"eliminate":[166],"need":[168],"linking":[170],"each":[171],"dataset":[173],"corresponding":[175],"hierarchies.":[176],"This":[177],"leads":[178],"improvements":[182],"critical":[184],"over":[188],"existing":[190],"state-of-the-art":[191],"models,":[193],"even":[194,207],"when":[195],"data":[197],"$is$":[198],"available":[199],"Moreover,":[202],"improvement":[204],"consistent":[206],"after":[208],"augmenting":[209],"our":[210],"baseline":[211],"support":[214],"We":[216],"conclude":[217],"discussing":[219],"how":[220],"implicit":[222],"structural":[223],"encodings":[224],"can":[225],"be":[226],"leveraged":[227],"beyond":[228],"domain.":[231]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}