{"id":"https://openalex.org/W4404569751","doi":"https://doi.org/10.1145/3820356.3820362","title":"Topological Data Analysis Applications in Natural Language Processing: A Survey","display_name":"Topological Data Analysis Applications in Natural Language Processing: A Survey","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W4404569751","doi":"https://doi.org/10.1145/3820356.3820362"},"language":"en","primary_location":{"id":"doi:10.1145/3820356.3820362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3820356.3820362","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.10298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075543864","display_name":"Adaku Uchendu","orcid":"https://orcid.org/0000-0001-7437-5153"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adaku Uchendu","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024109615","display_name":"Th\u00e1i Ho\u00e0ng L\u00ea","orcid":"https://orcid.org/0000-0002-6801-1924"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thai Le","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02145332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"1","first_page":"81","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.8992999792098999,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.8992999792098999,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/topological-data-analysis","display_name":"Topological data analysis","score":0.7387566566467285},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5028088092803955},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.45385676622390747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35085177421569824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3455837368965149},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3323313593864441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1184445321559906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08546721935272217},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.05614501237869263}],"concepts":[{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.7387566566467285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5028088092803955},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.45385676622390747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35085177421569824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3455837368965149},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3323313593864441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1184445321559906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08546721935272217},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.05614501237869263}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3820356.3820362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3820356.3820362","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2411.10298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10298","pdf_url":"https://arxiv.org/pdf/2411.10298","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2411.10298","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.10298","pdf_url":"https://arxiv.org/pdf/2411.10298","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.10298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.10298","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.10298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.10298","pdf_url":"https://arxiv.org/pdf/2411.10298","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":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":0,"referenced_works":[],"related_works":["https://openalex.org/W3036427183","https://openalex.org/W2886923060","https://openalex.org/W3119689987","https://openalex.org/W2291647075","https://openalex.org/W2635599261","https://openalex.org/W4283783782","https://openalex.org/W2887690685","https://openalex.org/W4295682319","https://openalex.org/W2965224253","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"surge":[1],"of":[2,12,16,72,102,138,186,233,257],"data":[3,55,150],"available":[4,260],"on":[5,95],"the":[6,10,51,70,96,240],"Internet":[7],"has":[8,32,133,160,188],"driven":[9],"adoption":[11],"a":[13,34,90,110,135,183,231,255],"wide":[14],"range":[15],"computational":[17],"methods":[18],"for":[19,40,113],"analyzing":[20],"and":[21,44,66,99,116,211,243,254],"extracting":[22],"insights":[23],"from":[24],"large-scale":[25],"data.":[26,103],"Among":[27],"these,":[28],"Machine":[29],"Learning":[30],"(ML)":[31],"become":[33],"central":[35],"paradigm,":[36],"offering":[37],"powerful":[38],"tools":[39],"pattern":[41],"discovery,":[42],"prediction,":[43],"representation":[45],"learning":[46],"across":[47],"many":[48],"domains.":[49],"At":[50],"same":[52],"time,":[53],"real-world":[54],"often":[56],"exhibit":[57],"properties":[58,118],"such":[59,83,178],"as":[60,179],"noise,":[61],"imbalance,":[62],"sparsity,":[63],"limited":[64,163],"supervision,":[65],"high":[67],"dimensionality,":[68],"motivating":[69],"use":[71,191,216],"additional":[73],"analytical":[74],"perspectives":[75],"that":[76,93,119,140,198,246],"can":[77],"complement":[78],"standard":[79],"ML":[80,144],"pipelines.":[81],"One":[82],"perspective":[84],"is":[85],"Topological":[86],"Data":[87],"Analysis":[88],"(TDA),":[89],"statistical":[91],"framework":[92],"focuses":[94],"intrinsic":[97],"shape":[98,249],"structural":[100,176],"organization":[101],"Rather":[104],"than":[105],"replacing":[106],"ML,":[107],"TDA":[108,142,159,226],"offers":[109],"complementary":[111],"lens":[112],"characterizing":[114],"geometric":[115],"topological":[117],"may":[120],"be":[121],"difficult":[122],"to":[123,171,195,218,248],"capture":[124],"with":[125,173],"conventional":[126],"feature-based":[127],"or":[128],"purely":[129],"predictive":[130],"approaches.":[131,213],"This":[132],"motivated":[134],"growing":[136],"body":[137],"work":[139],"integrates":[141],"into":[143,209,227],"workflows,":[145],"particularly":[146],"in":[147,165,192,202],"settings":[148],"where":[149],"structure":[151],"plays":[152],"an":[153],"important":[154],"role.":[155],"Despite":[156],"this":[157,203,250],"promise,":[158],"received":[161],"relatively":[162],"attention":[164],"Natural":[166],"Language":[167],"Processing":[168],"(NLP)":[169],"compared":[170],"domains":[172],"more":[174],"overt":[175],"regularities,":[177],"computer":[180],"vision.":[181],"Nevertheless,":[182],"dedicated":[184],"community":[185],"researchers":[187],"explored":[189],"its":[190],"NLP,":[193],"leading":[194],"137":[196],"papers":[197,258],"we":[199],"comprehensively":[200],"survey":[201],"work.":[204],"We":[205,236],"organize":[206],"these":[207],"studies":[208],"theoretical":[210],"nontheoretical":[212],"Theoretical":[214],"approaches":[215,224],"topology":[217],"explain":[219],"linguistic":[220],"phenomena,":[221],"whereas":[222],"non-theoretical":[223],"incorporate":[225],"ML-based":[228],"pipelines":[229],"through":[230],"variety":[232],"numerical":[234],"representations.":[235],"conclude":[237],"by":[238],"discussing":[239],"key":[241],"challenges":[242],"open":[244],"questions":[245],"continue":[247],"emerging":[251],"area.":[252],"Resources":[253],"list":[256],"are":[259],"at:":[261],"https://":[262],"github.com/AdaUchendu/AwesomeTDA4NLP.":[263]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2024-11-21T00:00:00"}