{"id":"https://openalex.org/W4415910706","doi":"https://doi.org/10.1155/cplx/9659172","title":"A Language and Its Holes: The First\u2010Order Homology of the Large\u2010Scale Geometrical Structure of a Natural Language","display_name":"A Language and Its Holes: The First\u2010Order Homology of the Large\u2010Scale Geometrical Structure of a Natural Language","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415910706","doi":"https://doi.org/10.1155/cplx/9659172"},"language":"en","primary_location":{"id":"doi:10.1155/cplx/9659172","is_oa":true,"landing_page_url":"https://doi.org/10.1155/cplx/9659172","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/cplx/9659172","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/cplx/9659172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012367531","display_name":"Vasilii A. Gromov","orcid":"https://orcid.org/0000-0001-5891-6597"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210160154","display_name":"Chemical Semantics (United States)","ror":"https://ror.org/04qca6973","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160154"]}],"countries":["RU","US"],"is_corresponding":true,"raw_author_name":"Vasilii A. Gromov","raw_affiliation_strings":["Laboratory of Analysis of Semantics ,  Centre for Language and Semantic Technologies ,  Faculty of Computer Science ,  HSE University ,  Moscow ,  Russia , hse.ru"],"raw_orcid":"https://orcid.org/0000-0001-5891-6597","affiliations":[{"raw_affiliation_string":"Laboratory of Analysis of Semantics ,  Centre for Language and Semantic Technologies ,  Faculty of Computer Science ,  HSE University ,  Moscow ,  Russia , hse.ru","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210160154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048289822","display_name":"Quynh Nhu Dang","orcid":"https://orcid.org/0000-0003-0450-7063"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210160154","display_name":"Chemical Semantics (United States)","ror":"https://ror.org/04qca6973","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160154"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Quynh Nhu Dang","raw_affiliation_strings":["Laboratory of Analysis of Semantics ,  Centre for Language and Semantic Technologies ,  Faculty of Computer Science ,  HSE University ,  Moscow ,  Russia , hse.ru"],"raw_orcid":"https://orcid.org/0000-0003-0450-7063","affiliations":[{"raw_affiliation_string":"Laboratory of Analysis of Semantics ,  Centre for Language and Semantic Technologies ,  Faculty of Computer Science ,  HSE University ,  Moscow ,  Russia , hse.ru","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210160154"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120262773","display_name":"Asel S. Erbolova","orcid":"https://orcid.org/0009-0007-7119-4665"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]},{"id":"https://openalex.org/I4210160154","display_name":"Chemical Semantics (United States)","ror":"https://ror.org/04qca6973","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160154"]}],"countries":["RU","US"],"is_corresponding":false,"raw_author_name":"Asel S. Erbolova","raw_affiliation_strings":["Laboratory of Analysis of Semantics ,  Centre for Language and Semantic Technologies ,  Faculty of Computer Science ,  HSE University ,  Moscow ,  Russia , hse.ru"],"raw_orcid":"https://orcid.org/0009-0007-7119-4665","affiliations":[{"raw_affiliation_string":"Laboratory of Analysis of Semantics ,  Centre for Language and Semantic Technologies ,  Faculty of Computer Science ,  HSE University ,  Moscow ,  Russia , hse.ru","institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210160154"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012367531"],"corresponding_institution_ids":["https://openalex.org/I118501908","https://openalex.org/I4210160154"],"apc_list":{"value":2550,"currency":"USD","value_usd":2550},"apc_paid":{"value":2550,"currency":"USD","value_usd":2550},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27048119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9961000084877014,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10896","display_name":"Homotopy and Cohomology in Algebraic Topology","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10948","display_name":"Advanced Combinatorial Mathematics","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2607","display_name":"Discrete Mathematics and Combinatorics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.862500011920929},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5277000069618225},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5196999907493591},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47290000319480896},{"id":"https://openalex.org/keywords/persistent-homology","display_name":"Persistent homology","score":0.42170000076293945},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.862500011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579200029373169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5511999726295471},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C2874115","wikidata":"https://www.wikidata.org/wiki/Q17099562","display_name":"Persistent homology","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.38769999146461487},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2700999975204468}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/cplx/9659172","is_oa":true,"landing_page_url":"https://doi.org/10.1155/cplx/9659172","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/cplx/9659172","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:05c23da0e1184869ab4d20a7d1df2218","is_oa":true,"landing_page_url":"https://doaj.org/article/05c23da0e1184869ab4d20a7d1df2218","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complexity, Vol 2025 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/cplx/9659172","is_oa":true,"landing_page_url":"https://doi.org/10.1155/cplx/9659172","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/cplx/9659172","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324261","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415910706.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1983541773","https://openalex.org/W1985755506","https://openalex.org/W2026940923","https://openalex.org/W2241038958","https://openalex.org/W2252131670","https://openalex.org/W2319717399","https://openalex.org/W2768672809","https://openalex.org/W2887121766","https://openalex.org/W2901191984","https://openalex.org/W2936324353","https://openalex.org/W2969372718","https://openalex.org/W2996686709","https://openalex.org/W3004917954","https://openalex.org/W3122213525","https://openalex.org/W3144454328","https://openalex.org/W3171131780","https://openalex.org/W3202156680","https://openalex.org/W3203429167","https://openalex.org/W4200147087","https://openalex.org/W4210543124","https://openalex.org/W4225271072","https://openalex.org/W4308325149","https://openalex.org/W4313592093","https://openalex.org/W4382599626","https://openalex.org/W4385949164","https://openalex.org/W4386886274","https://openalex.org/W4390102235","https://openalex.org/W4392107999","https://openalex.org/W4400063766"],"related_works":[],"abstract_inverted_index":{"The":[0,110,181],"present":[1],"paper":[2,36,115],"employs":[3],"topological":[4],"data":[5],"analysis":[6],"methods":[7],"to":[8,30,42,117,161,191],"reveal":[9],"\u2018holes\u2019":[10],"(stable":[11],"persistent":[12],"homologies)":[13],"in":[14,122],"the":[15,24,35,43,48,57,71,82,87,96,103,114,119,130,140,150,162,165,187],"semantic":[16,88],"spaces":[17,89],"of":[18,23,47,56,66,70,81,86,95,100,113,135,143,158,164],"words,":[19,154],"bigrams,":[20,155],"and":[21,26,29,74,137,156,174,178],"trigrams":[22,157],"English":[25],"Russian":[27],"languages,":[28],"ascertain":[31],"their":[32],"boundaries.":[33],"Furthermore,":[34],"selects":[37],"those":[38],"holes":[39],"that":[40,50,60,90,102,126],"belong":[41],"large\u2010scale":[44],"(coarse\u2010grained)":[45],"structure":[46],"language":[49,104],"are":[51,62],"not":[52,92],"just":[53],"local":[54],"inhomogeneities":[55],"sample\u2014it":[58],"appears":[59],"there":[61],"around":[63],"a":[64,159],"dozen":[65],"them":[67],"for":[68,168],"each":[69],"languages":[72],"(English":[73],"Russian).":[75],"These":[76],"boundaries":[77,163],"delineate":[78],"\u2018blind":[79],"spots\u2019":[80],"respective":[83],"language\u2014the":[84],"regions":[85,99],"do":[91],"contain":[93],"words/bigrams/trigrams":[94],"language\u2014that":[97],"is,":[98,127],"concepts":[101],"cannot":[105],"see":[106],"through":[107],"its":[108,123],"lens.":[109],"secondary":[111],"goal":[112],"is":[116],"solve":[118],"bot\u2010detection":[120],"problem":[121],"strong":[124],"statement,":[125],"one":[128,133],"trains":[129],"classifiers":[131,182],"on":[132,139],"set":[134,142],"bots":[136],"tests":[138],"another":[141],"bots.":[144],"To":[145],"this":[146],"end,":[147],"we":[148],"estimate":[149],"average":[151,188],"distances":[152],"from":[153],"text":[160],"nearest":[166],"\u2018hole\u2019,":[167],"texts":[169],"both":[170],"written":[171],"by":[172,176],"humans":[173],"generated":[175],"bots,":[177],"construct":[179],"classifiers.":[180],"show":[183],"comparatively":[184],"good":[185],"results:":[186],"accuracy":[189],"amounts":[190],"0.8.":[192]},"counts_by_year":[],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-11-05T00:00:00"}