{"id":"https://openalex.org/W4387619775","doi":"https://doi.org/10.15439/2023f9253","title":"Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders","display_name":"Passage Retrieval of Polish Texts Using OKAPI BM25 and an Ensemble of Cross Encoders","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4387619775","doi":"https://doi.org/10.15439/2023f9253"},"language":"en","primary_location":{"id":"doi:10.15439/2023f9253","is_oa":true,"landing_page_url":"http://dx.doi.org/10.15439/2023f9253","pdf_url":"https://annals-csis.org/Volume_35/drp/pdf/9253.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/Volume_35/drp/pdf/9253.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055549839","display_name":"Jakub Pokrywka","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jakub Pokrywka","raw_affiliation_strings":["University Faculty of Mathematics and Computer Science,"],"affiliations":[{"raw_affiliation_string":"University Faculty of Mathematics and Computer Science,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055549839"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15428277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1265","last_page":"1269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T11719","display_name":"Data Quality and Management","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8542362451553345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6390380859375},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6363312602043152},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6340610384941101},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6112967729568481},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5899323225021362},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43927937746047974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542362451553345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6390380859375},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6363312602043152},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6340610384941101},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6112967729568481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5899323225021362},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43927937746047974},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2023f9253","is_oa":true,"landing_page_url":"http://dx.doi.org/10.15439/2023f9253","pdf_url":"https://annals-csis.org/Volume_35/drp/pdf/9253.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.04620","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.04620","pdf_url":"https://arxiv.org/pdf/2410.04620","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":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:bdc3ea432c0845ceb41036978e040efd","is_oa":true,"landing_page_url":"https://doaj.org/article/bdc3ea432c0845ceb41036978e040efd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 35, Pp 1265-1269 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2023f9253","is_oa":true,"landing_page_url":"http://dx.doi.org/10.15439/2023f9253","pdf_url":"https://annals-csis.org/Volume_35/drp/pdf/9253.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387619775.pdf","grobid_xml":"https://content.openalex.org/works/W4387619775.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2558203065","https://openalex.org/W2951534261","https://openalex.org/W2972594731","https://openalex.org/W2983040767","https://openalex.org/W3017604292","https://openalex.org/W3033187248","https://openalex.org/W3033862527","https://openalex.org/W3035390927","https://openalex.org/W3082928416","https://openalex.org/W3093517588","https://openalex.org/W3097571385","https://openalex.org/W3100806282","https://openalex.org/W3113565477","https://openalex.org/W3122890974","https://openalex.org/W3155292524","https://openalex.org/W3157789198","https://openalex.org/W3169483174","https://openalex.org/W3174544005","https://openalex.org/W3198713493","https://openalex.org/W4280575577","https://openalex.org/W4287018294","https://openalex.org/W4379087931","https://openalex.org/W7054915730"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Passage":[0,50],"Retrieval":[1,51],"has":[2],"traditionally":[3],"relied":[4],"on":[5],"lexical":[6],"methods":[7,19],"like":[8],"TF-IDF":[9],"and":[10,34,65,76,88],"BM25.Recently,":[11],"some":[12],"neural":[13],"network":[14],"models":[15,23,101],"have":[16],"surpassed":[17],"these":[18,22],"in":[20,60,107,114],"performance.However,":[21],"face":[24],"challenges,":[25],"such":[26],"as":[27],"the":[28,45,69,81,99,108],"need":[29],"for":[30,74,97],"large":[31],"annotated":[32],"datasets":[33],"adapting":[35],"to":[36,44,85],"new":[37],"domains.This":[38],"paper":[39],"presents":[40],"a":[41],"winning":[42],"solution":[43],"Poleval":[46],"2023":[47],"Task":[48],"3:":[49],"challenge,":[52],"which":[53],"involves":[54],"retrieving":[55],"passages":[56],"of":[57,91],"Polish":[58],"texts":[59],"three":[61],"domains:":[62],"trivia,":[63],"legal,":[64],"customer":[66],"support.However,":[67],"only":[68,106],"trivia":[70],"domain":[71],"was":[72],"used":[73,80],"training":[75,109],"development":[77],"data.The":[78],"method":[79],"OKAPI":[82],"BM25":[83],"algorithm":[84],"retrieve":[86],"documents":[87],"an":[89],"ensemble":[90],"publicly":[92],"available":[93],"multilingual":[94],"Cross":[95],"Encoders":[96],"Reranking.Fine-tuning":[98],"reranker":[100],"slightly":[102],"improved":[103],"performance":[104],"but":[105],"domain,":[110],"while":[111],"it":[112],"worsened":[113],"other":[115],"domains.":[116]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-10-14T00:00:00"}
