{"id":"https://openalex.org/W4390091249","doi":"https://doi.org/10.48550/arxiv.2312.11276","title":"Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach","display_name":"Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W4390091249","doi":"https://doi.org/10.48550/arxiv.2312.11276"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2312.11276","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.11276","pdf_url":"https://arxiv.org/pdf/2312.11276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.11276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072026861","display_name":"Yuyang Chai","orcid":"https://orcid.org/0000-0001-9108-370X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chai, Yuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076694","display_name":"Zhuang Li","orcid":"https://orcid.org/0009-0006-3870-4275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326015","display_name":"Jiahui Liu","orcid":"https://orcid.org/0009-0008-1231-4257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064062823","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-4912-3293"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325880","display_name":"Fei Li","orcid":"https://orcid.org/0000-0003-1372-3999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058877618","display_name":"Donghong Ji","orcid":"https://orcid.org/0000-0001-9613-5927"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Donghong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101895693","display_name":"Chong Teng","orcid":"https://orcid.org/0009-0008-6543-2548"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng, Chong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072026861"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9891999959945679,"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/T10028","display_name":"Topic Modeling","score":0.9690999984741211,"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/generalization","display_name":"Generalization","score":0.9061846733093262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7252140045166016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5251878499984741},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5212239027023315},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43748176097869873},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4070083498954773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3641016483306885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11104825139045715}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.9061846733093262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252140045166016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251878499984741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5212239027023315},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43748176097869873},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4070083498954773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3641016483306885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11104825139045715},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2312.11276","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.11276","pdf_url":"https://arxiv.org/pdf/2312.11276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2312.11276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2312.11276","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.11276","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.11276","pdf_url":"https://arxiv.org/pdf/2312.11276","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1453686608","display_name":null,"funder_award_id":"62176187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390091249.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4200527723"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"advancements":[2],"in":[3],"multi-label":[4,49],"text":[5,50,93,132],"classification,":[6],"the":[7,43,99,116],"ability":[8,46],"of":[9,23,47,120],"existing":[10,48],"models":[11,58,95,122,129],"to":[12,14,61,63,71,97],"generalize":[13,62],"novel":[15],"and":[16],"seldom-encountered":[17],"complex":[18],"concepts,":[19],"which":[20],"are":[21],"compositions":[22],"elementary":[24],"ones,":[25],"remains":[26],"underexplored.":[27],"This":[28],"research":[29],"addresses":[30],"this":[31,110],"gap.":[32],"By":[33],"creating":[34],"unique":[35],"data":[36,86,111],"splits":[37],"across":[38],"three":[39],"benchmarks,":[40,125],"we":[41,83],"assess":[42],"compositional":[44,64,104,117],"generalization":[45,118],"classification":[51,100,121],"models.":[52],"Our":[53,106],"results":[54],"show":[55,108],"that":[56,89,109],"these":[57,77],"often":[59],"fail":[60],"concepts":[65],"encountered":[66],"infrequently":[67],"during":[68],"training,":[69],"leading":[70],"inferior":[72],"performance":[73],"on":[74,123],"tests":[75],"with":[76,126],"new":[78],"combinations.":[79],"To":[80],"address":[81],"this,":[82],"introduce":[84],"a":[85],"augmentation":[87,112],"method":[88],"leverages":[90],"two":[91],"innovative":[92],"generation":[94,128,133],"designed":[96],"enhance":[98],"models'":[101],"capacity":[102],"for":[103],"generalization.":[105],"experiments":[107],"approach":[113],"significantly":[114],"improves":[115],"capabilities":[119],"our":[124],"both":[127],"surpassing":[130],"other":[131],"baselines.":[134]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2023-12-22T00:00:00"}