{"id":"https://openalex.org/W4400762692","doi":"https://doi.org/10.1145/3626772.3657949","title":"Large Language Models Based Stemming for Information Retrieval: Promises, Pitfalls and Failures","display_name":"Large Language Models Based Stemming for Information Retrieval: Promises, Pitfalls and Failures","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400762692","doi":"https://doi.org/10.1145/3626772.3657949"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100328263","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-0726-5250"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["The University of Queensland Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0726-5250","affiliations":[{"raw_affiliation_string":"The University of Queensland Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012958162","display_name":"Shengyao Zhuang","orcid":"https://orcid.org/0000-0002-6711-0955"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shengyao Zhuang","raw_affiliation_strings":["CSIRO, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6711-0955","affiliations":[{"raw_affiliation_string":"CSIRO, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["The University of Queensland Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0271-5563","affiliations":[{"raw_affiliation_string":"The University of Queensland Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100328263"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":2.1884,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89174039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2492","last_page":"2496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.9937000274658203,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9854000210762024,"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":0.7863808274269104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4610876441001892},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4451257884502411},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3847929537296295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32057780027389526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863808274269104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4610876441001892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4451257884502411},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3847929537296295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32057780027389526}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2002639244","https://openalex.org/W2058200372","https://openalex.org/W2098162425","https://openalex.org/W2790055648","https://openalex.org/W2945127593","https://openalex.org/W3099446234","https://openalex.org/W3180230246","https://openalex.org/W4238677011","https://openalex.org/W4284669679","https://openalex.org/W4313680149","https://openalex.org/W4384641573","https://openalex.org/W4384642697","https://openalex.org/W4385573057","https://openalex.org/W4385688511","https://openalex.org/W4388948240","https://openalex.org/W4388955618","https://openalex.org/W4391136507","https://openalex.org/W4400527956","https://openalex.org/W4401043313","https://openalex.org/W6600076646","https://openalex.org/W6600104757","https://openalex.org/W6600829110","https://openalex.org/W6601548533","https://openalex.org/W6880033799"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text":[0],"stemming":[1,28,55,72],"is":[2,9,29],"a":[3],"natural":[4],"language":[5],"processing":[6,42],"technique":[7],"that":[8],"used":[10,30],"to":[11,14,35,43,59],"reduce":[12],"words":[13],"their":[15],"base":[16],"form,":[17],"also":[18],"known":[19],"as":[20,68],"the":[21,62,80],"root":[22],"form.":[23],"In":[24],"Information":[25],"Retrieval":[26],"(IR),":[27],"in":[31],"keyword-based":[32],"matching":[33,46],"pipelines":[34],"normalise":[36],"text":[37],"before":[38],"indexing":[39],"and":[40,49],"query":[41,50],"improve":[44,61],"subsequent":[45],"between":[47],"document":[48],"keywords.":[51],"The":[52],"use":[53],"of":[54,64,82],"has":[56],"been":[57],"shown":[58],"often":[60],"effectiveness":[63],"keyword-matching":[65],"models":[66],"such":[67],"BM25.":[69],"However,":[70],"traditional":[71],"methods,":[73],"focusing":[74],"solely":[75],"on":[76],"individual":[77],"terms,":[78],"overlook":[79],"richness":[81],"contextual":[83],"information.":[84]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}