{"id":"https://openalex.org/W4410825142","doi":"https://doi.org/10.1145/3716554.3716833","title":"Comparison of a Semi-Automatically Generated and a Manually Created Linguistic Rule-Based Stemmer for Polish by a Polish Native Speaker","display_name":"Comparison of a Semi-Automatically Generated and a Manually Created Linguistic Rule-Based Stemmer for Polish by a Polish Native Speaker","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4410825142","doi":"https://doi.org/10.1145/3716554.3716833"},"language":"en","primary_location":{"id":"doi:10.1145/3716554.3716833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3716554.3716833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3716554.3716833","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 28th Pan-Hellenic Conference on Progress in Computing and Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3716554.3716833","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081787499","display_name":"Nikitas \u039d. Karanikolas","orcid":"https://orcid.org/0000-0003-1777-892X"},"institutions":[{"id":"https://openalex.org/I4210094138","display_name":"University of West Attica","ror":"https://ror.org/00r2r5k05","country_code":"GR","type":"education","lineage":["https://openalex.org/I4210094138"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikitas N. Karanikolas","raw_affiliation_strings":["Informatics and Computer Engineering, University of West Attica, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0003-1777-892X","affiliations":[{"raw_affiliation_string":"Informatics and Computer Engineering, University of West Attica, Athens, Greece","institution_ids":["https://openalex.org/I4210094138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117730118","display_name":"Mateusz Zywczak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094138","display_name":"University of West Attica","ror":"https://ror.org/00r2r5k05","country_code":"GR","type":"education","lineage":["https://openalex.org/I4210094138"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Mateusz Zywczak","raw_affiliation_strings":["Informatics and Computer Engineering, University of West Attica, Athens, Greece"],"raw_orcid":"https://orcid.org/0009-0006-7515-0486","affiliations":[{"raw_affiliation_string":"Informatics and Computer Engineering, University of West Attica, Athens, Greece","institution_ids":["https://openalex.org/I4210094138"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210094138"],"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":"351","last_page":"357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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/T12658","display_name":"Language and Culture","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9652000069618225,"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":0.6784228682518005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5881399512290955},{"id":"https://openalex.org/keywords/rule-based-system","display_name":"Rule-based system","score":0.5874696373939514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779609084129333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5724279880523682},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.49101021885871887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784228682518005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5881399512290955},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.5874696373939514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779609084129333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5724279880523682},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.49101021885871887},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3716554.3716833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3716554.3716833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3716554.3716833","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 28th Pan-Hellenic Conference on Progress in Computing and Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3716554.3716833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3716554.3716833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3716554.3716833","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 28th Pan-Hellenic Conference on Progress in Computing and Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410825142.pdf","grobid_xml":"https://content.openalex.org/works/W4410825142.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1968951234","https://openalex.org/W1969764407","https://openalex.org/W2032760722","https://openalex.org/W2124447821","https://openalex.org/W2584160550","https://openalex.org/W4246570783","https://openalex.org/W6927580526"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W4387849428","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Usually,":[0],"Stemmers":[1],"are":[2,33,44,117,174,182],"manually":[3],"created":[4],"by":[5,133],"native":[6,135],"target":[7,27,71,97,139],"language":[8,28,72,98],"speakers,":[9],"on":[10,47,160],"the":[11,26,55,70,122,138,155,164],"basis":[12],"of":[13,25,39,50,69,96,102,137,151,166,185],"rules":[14],"for":[15,36,60,89],"suffix":[16],"stripping":[17],"or":[18],"replacements.":[19],"In":[20,64,106],"such":[21,65],"cases":[22,66],"linguistic":[23,67,94,149],"knowledge":[24,68,95,150],"is":[29,73,104,113,145,158,170],"a":[30,79,134],"requirement.":[31],"There":[32],"also":[34],"approaches":[35,43],"automatic":[37],"creation":[38],"stemmers.":[40],"The":[41,142,172],"later":[42],"usually":[45],"based":[46,159],"statistical":[48,100],"processing":[49,101],"text":[51],"corpuses":[52,103],"to":[53,178],"calculate":[54],"occurrences":[56],"and":[57,62,154,176],"other":[58],"metrics":[59],"stems":[61],"affixes.":[63],"not":[74],"needed.":[75,105,114],"We":[76],"have":[77,84],"invented":[78],"semi-automatic":[80],"methodology":[81,162],"(and":[82],"we":[83,116,129],"made":[85],"an":[86],"equivalent":[87],"implementation)":[88],"Stemmer":[90,144],"generation":[91],"that":[92],"neither":[93],"nor":[99],"our":[107,119,161,186],"approach":[108,120],"only":[109],"Information":[110,167],"Retrieval":[111,168],"expertise":[112],"Here":[115],"evaluating":[118],"against":[121],"rule-based":[123,146],"(linguistic-knowledge-based)":[124],"approach.":[125],"To":[126],"do":[127],"so":[128],"evaluate":[130],"two":[131],"stemmers":[132],"speaker":[136],"(Polish)":[140],"language.":[141],"first":[143],"(it":[147],"incorporates":[148],"Polish":[152],"language)":[153],"second":[156],"one":[157],"(only":[163],"experience":[165],"Experts":[169],"incorporated).":[171],"results":[173],"interesting":[175],"hard":[177],"wait":[179],"for,":[180],"they":[181],"in":[183],"favor":[184],"methodology.":[187]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
