{"id":"https://openalex.org/W4293083967","doi":"https://doi.org/10.1145/3542822","title":"Supervised Contrastive Learning for Interpretable Long-Form Document Matching","display_name":"Supervised Contrastive Learning for Interpretable Long-Form Document Matching","publication_year":2022,"publication_date":"2022-06-11","ids":{"openalex":"https://openalex.org/W4293083967","doi":"https://doi.org/10.1145/3542822"},"language":"en","primary_location":{"id":"doi:10.1145/3542822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3542822","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3542822","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3542822","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005165729","display_name":"Akshita Jha","orcid":"https://orcid.org/0000-0003-2330-6806"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshita Jha","raw_affiliation_strings":["Virginia Tech, Arlington, VA"],"raw_orcid":"https://orcid.org/0000-0003-2330-6806","affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000202397","display_name":"Vineeth Rakesh","orcid":"https://orcid.org/0000-0001-7586-0257"},"institutions":[{"id":"https://openalex.org/I36326968","display_name":"InterDigital (United States)","ror":"https://ror.org/02w335z67","country_code":"US","type":"company","lineage":["https://openalex.org/I36326968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vineeth Rakesh","raw_affiliation_strings":["InterDigital, Los Altos, CA"],"raw_orcid":"https://orcid.org/0000-0001-7586-0257","affiliations":[{"raw_affiliation_string":"InterDigital, Los Altos, CA","institution_ids":["https://openalex.org/I36326968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089322398","display_name":"Jaideep Chandrashekar","orcid":"https://orcid.org/0000-0003-4615-7487"},"institutions":[{"id":"https://openalex.org/I36326968","display_name":"InterDigital (United States)","ror":"https://ror.org/02w335z67","country_code":"US","type":"company","lineage":["https://openalex.org/I36326968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaideep Chandrashekar","raw_affiliation_strings":["InterDigital, Los Altos, CA"],"raw_orcid":"https://orcid.org/0000-0003-4615-7487","affiliations":[{"raw_affiliation_string":"InterDigital, Los Altos, CA","institution_ids":["https://openalex.org/I36326968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087404235","display_name":"Adithya Samavedhi","orcid":"https://orcid.org/0000-0002-9232-6395"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adithya Samavedhi","raw_affiliation_strings":["Virginia Tech, Arlington, VA"],"raw_orcid":"https://orcid.org/0000-0002-9232-6395","affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001022750","display_name":"Chandan K. Reddy","orcid":"https://orcid.org/0000-0003-2839-3662"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandan K. Reddy","raw_affiliation_strings":["Virginia Tech, Arlington, VA"],"raw_orcid":"https://orcid.org/0000-0003-2839-3662","affiliations":[{"raw_affiliation_string":"Virginia Tech, Arlington, VA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9682,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88185445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9776999950408936,"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":0.7564127445220947},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7192222476005554},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6949297785758972},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6562207937240601},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6271259784698486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5675249099731445},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.54203200340271},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.46000343561172485},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4195743203163147},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4182620048522949},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1531912088394165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08327797055244446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564127445220947},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7192222476005554},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6949297785758972},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6562207937240601},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6271259784698486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5675249099731445},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.54203200340271},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.46000343561172485},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4195743203163147},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4182620048522949},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1531912088394165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08327797055244446},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3542822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3542822","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3542822","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/112054","is_oa":false,"landing_page_url":"http://hdl.handle.net/10919/112054","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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":"Article - Refereed"}],"best_oa_location":{"id":"doi:10.1145/3542822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3542822","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3542822","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G4782360968","display_name":"SCH: INT: Collaborative Research: Data-driven Stratification and  Prognosis for Traumatic Brain Injury","funder_award_id":"1838730","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7817772119","display_name":null,"funder_award_id":"IIS-1838730","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293083967.pdf","grobid_xml":"https://content.openalex.org/works/W4293083967.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1531333757","https://openalex.org/W1583837637","https://openalex.org/W2028742638","https://openalex.org/W2136189984","https://openalex.org/W2178628967","https://openalex.org/W2286300105","https://openalex.org/W2470673105","https://openalex.org/W2510530102","https://openalex.org/W2536015822","https://openalex.org/W2538374209","https://openalex.org/W2539671052","https://openalex.org/W2559655401","https://openalex.org/W2750779823","https://openalex.org/W2769216919","https://openalex.org/W2885396331","https://openalex.org/W2911997761","https://openalex.org/W2950670227","https://openalex.org/W2962807820","https://openalex.org/W2963798744","https://openalex.org/W2964110616","https://openalex.org/W2970641574","https://openalex.org/W2970726176","https://openalex.org/W2990138404","https://openalex.org/W3019932981","https://openalex.org/W3093838622","https://openalex.org/W3106298483","https://openalex.org/W3108316907","https://openalex.org/W3156636935","https://openalex.org/W3173783447"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,89,161,202,215,251],"deep":[3],"learning":[4,167],"techniques":[5],"have":[6,37],"transformed":[7],"the":[8,64,70,74,90,95,102,115,118,203,237,241,264],"area":[9],"of":[10,66,79,98,105,117,147,183],"semantic":[11],"text":[12,82,88,255],"matching":[13,243],"(STM).":[14],"However,":[15],"most":[16],"state-of-the-art":[17,238],"models":[18,36],"are":[19,59],"designed":[20],"to":[21,42,113,169,249],"operate":[22],"with":[23,163],"short":[24],"documents":[25,44],"such":[26,45,55],"as":[27,46],"tweets,":[28],"user":[29],"reviews,":[30],"comments,":[31],"and":[32,51,100,142,155,192,195,206,232,254,257],"so":[33],"on.":[34],"These":[35,210],"fundamental":[38],"limitations":[39],"when":[40],"applied":[41],"long-form":[43],"scientific":[47],"papers,":[48],"legal":[49],"documents,":[50,57,85,184,194],"patents.":[52,234],"When":[53],"handling":[54],"long":[56,148,223],"there":[58],"three":[60,173,222],"primary":[61],"challenges:":[62],"(i)":[63,176],"presence":[65],"different":[67,174,189,200],"contexts":[68],"for":[69,144,263],"same":[71,204],"word":[72],"throughout":[73],"document,":[75],"(ii)":[76,185],"small":[77],"sections":[78,190],"contextually":[80],"similar":[81],"between":[83,180,188,199],"two":[84],"but":[86],"dissimilar":[87],"remaining":[91],"parts":[92],"(this":[93],"defies":[94],"basic":[96],"understanding":[97],"\u201csimilarity\u201d),":[99],"(iii)":[101,196],"coarse":[103],"nature":[104],"a":[106,156,164,181],"single":[107],"global":[108],"similarity":[109,171,178,186,197,212],"measure":[110],"which":[111],"fails":[112],"capture":[114,170],"heterogeneity":[116],"document":[119,205,224,242,252],"content.":[120],"In":[121],"this":[122],"article,":[123],"we":[124],"describe":[125],"CoLDE":[126,150,220,245],":":[127],"Co":[128],"ntrastive":[129],"L":[130],"ong":[131],"D":[132],"ocument":[133],"E":[134],"ncoder\u2014a":[135],"transformer-based":[136],"framework":[137,168],"that":[138],"addresses":[139],"these":[140],"challenges":[141],"allows":[143],"interpretable":[145,259],"comparisons":[146],"documents.":[149,209],"uses":[151],"unique":[152],"positional":[153],"embeddings":[154],"multi-headed":[157],"chunkwise":[158],"attention":[159],"layer":[160],"conjunction":[162],"supervised":[165],"contrastive":[166],"at":[172,270],"levels:":[175],"high-level":[177],"scores":[179,187,198,213],"pair":[182],"within":[191],"across":[193,207],"chunks":[201],"other":[208],"fine-grained":[211],"aid":[214],"better":[216],"interpretability.":[217],"We":[218],"evaluate":[219],"on":[221,240],"datasets":[225],"namely,":[226],"ACL":[227],"Anthology":[228],"publications,":[229],"Wikipedia":[230],"articles,":[231],"USPTO":[233],"Besides":[235],"outperforming":[236],"methods":[239],"task,":[244],"is":[246,267],"also":[247],"robust":[248],"changes":[250],"length":[253],"perturbations":[256],"provides":[258],"results.":[260],"The":[261],"code":[262],"proposed":[265],"model":[266],"publicly":[268],"available":[269],"https://github.com/InterDigitalInc/CoLDE":[271],".":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}