{"id":"https://openalex.org/W2740995790","doi":"https://doi.org/10.18653/v1/w17-1415","title":"Comparison of String Similarity Measures for Obscenity Filtering","display_name":"Comparison of String Similarity Measures for Obscenity Filtering","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740995790","doi":"https://doi.org/10.18653/v1/w17-1415","mag":"2740995790"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1415","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1415","pdf_url":"https://www.aclweb.org/anthology/W17-1415.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-1415.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051011436","display_name":"Ekaterina Chernyak","orcid":null},"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"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Ekaterina Chernyak","raw_affiliation_strings":["National Research University Higher School of Economics Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research University Higher School of Economics Moscow, Russia","institution_ids":["https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051011436"],"corresponding_institution_ids":["https://openalex.org/I118501908"],"apc_list":null,"apc_paid":null,"fwci":0.4313,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6007599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9991999864578247,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/string-metric","display_name":"String metric","score":0.7805448770523071},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6938948631286621},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6706084609031677},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.639187216758728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6314049959182739},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.571048378944397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5413283109664917},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5399503707885742},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5197591185569763},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5148674249649048},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5035285353660583},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.43899890780448914},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.435455322265625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36695656180381775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2691164016723633},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22417965531349182},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14082348346710205},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.09229186177253723}],"concepts":[{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7805448770523071},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6938948631286621},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6706084609031677},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.639187216758728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6314049959182739},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.571048378944397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5413283109664917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5399503707885742},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5197591185569763},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5148674249649048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5035285353660583},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.43899890780448914},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.435455322265625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36695656180381775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2691164016723633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22417965531349182},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14082348346710205},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.09229186177253723},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-1415","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1415","pdf_url":"https://www.aclweb.org/anthology/W17-1415.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-1415","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1415","pdf_url":"https://www.aclweb.org/anthology/W17-1415.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G197055748","display_name":null,"funder_award_id":"5\u2010100","funder_id":"https://openalex.org/F4320324261","funder_display_name":"National Research University Higher School of Economics"},{"id":"https://openalex.org/G4711892333","display_name":null,"funder_award_id":"5-100","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"},{"id":"https://openalex.org/G5260489559","display_name":null,"funder_award_id":"16-01-00583","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"},{"id":"https://openalex.org/G6521856933","display_name":null,"funder_award_id":"16-29-12982","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"}],"funders":[{"id":"https://openalex.org/F4320321079","display_name":"Russian Foundation for Basic Research","ror":"https://ror.org/02mh1ke95"},{"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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740995790.pdf","grobid_xml":"https://content.openalex.org/works/W2740995790.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W52972111","https://openalex.org/W1492737170","https://openalex.org/W1532325895","https://openalex.org/W1601432161","https://openalex.org/W1986921409","https://openalex.org/W2045929671","https://openalex.org/W2049271634","https://openalex.org/W2066102695","https://openalex.org/W2077388026","https://openalex.org/W2100958137","https://openalex.org/W2108991785","https://openalex.org/W2116091861","https://openalex.org/W2167435923","https://openalex.org/W2171313960","https://openalex.org/W2263859238","https://openalex.org/W2604646253","https://openalex.org/W2786144004","https://openalex.org/W3146259567"],"related_works":["https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2405436873","https://openalex.org/W2131677984","https://openalex.org/W1548380832","https://openalex.org/W52396946","https://openalex.org/W1593185626","https://openalex.org/W1973578339","https://openalex.org/W3022344494","https://openalex.org/W1824878879"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"address":[4],"the":[5,41,54,64],"problem":[6],"of":[7,56,63],"filtering":[8],"obscene":[9],"lexis":[10],"in":[11],"Russian":[12],"texts.":[13],"We":[14],"use":[15],"string":[16,49],"similarity":[17,50],"measures":[18],"to":[19,25],"find":[20],"words":[21,26],"similar":[22],"or":[23],"identical":[24],"from":[27],"a":[28,34,38,47],"stop":[29],"list":[30],"and":[31,37],"establish":[32],"both":[33],"test":[35],"collection":[36],"baseline":[39],"for":[40],"task.":[42],"Our":[43],"experiments":[44],"show":[45],"that":[46],"novel":[48],"measure":[51],"based":[52],"on":[53],"notion":[55],"an":[57],"annotated":[58],"suffix":[59],"tree":[60],"outperforms":[61],"some":[62],"other":[65],"well":[66],"known":[67],"measures.":[68]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}