{"id":"https://openalex.org/W4412944927","doi":"https://doi.org/10.18653/v1/2025.acl-long.930","title":"Enhancing Lexicon-Based Text Embeddings with Large Language Models","display_name":"Enhancing Lexicon-Based Text Embeddings with Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944927","doi":"https://doi.org/10.18653/v1/2025.acl-long.930"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.930","pdf_url":"https://aclanthology.org/2025.acl-long.930.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.930.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080310094","display_name":"Yibin Lei","orcid":"https://orcid.org/0009-0007-9558-5548"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibin Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611243","display_name":"Tao Shen","orcid":"https://orcid.org/0000-0003-3315-2468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103124835","display_name":"Yu Cao","orcid":"https://orcid.org/0000-0002-2630-2475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059489981","display_name":"Andrew Yates","orcid":"https://orcid.org/0000-0002-5970-880X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Yates","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6796,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87453665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"18986","last_page":"19001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.9945999979972839,"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":0.9818000197410583,"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/lexicon","display_name":"Lexicon","score":0.8160123825073242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7849752306938171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6967969536781311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5841748118400574},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43379735946655273},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3329398036003113}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8160123825073242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849752306938171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6967969536781311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5841748118400574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43379735946655273},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3329398036003113},{"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:10.18653/v1/2025.acl-long.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.930","pdf_url":"https://aclanthology.org/2025.acl-long.930.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.930","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.930","pdf_url":"https://aclanthology.org/2025.acl-long.930.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G6283025712","display_name":"IDEAS: Incremental Dense Representations","funder_award_id":"VI.Vidi.223.166","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944927.pdf","grobid_xml":"https://content.openalex.org/works/W4412944927.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W1831473261","https://openalex.org/W4293870971","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5,16],"demonstrated":[6],"exceptional":[7],"performance":[8,32,133],"on":[9,33,95,134],"general-purpose":[10],"text":[11],"embedding":[12,42,115],"tasks.While":[13],"dense":[14,93,109,129],"embeddings":[15,25,94,130],"dominated":[17],"related":[18],"research,":[19],"we":[20,57],"introduce":[21],"the":[22,37,46,96,135],"first":[23],"lexicon-based":[24],"(LENS)":[26],"leveraging":[27],"LLMs":[28],"that":[29,90],"achieve":[30],"competitive":[31],"these":[34],"tasks.LENS":[35],"consolidates":[36],"vocabulary":[38],"space":[39],"through":[40],"token":[41,49,79],"clustering":[43],"to":[44,76,108],"handle":[45],"issue":[47],"of":[48,138],"redundancy":[50],"in":[51],"LLM":[52],"vocabularies.To":[53],"further":[54],"improve":[55],"performance,":[56],"investigate":[58],"bidirectional":[59],"attention":[60],"and":[61],"various":[62],"pooling":[63],"strategies.Specifically,":[64],"LENS":[65,91,111,127],"simplifies":[66],"lexical":[67],"matching":[68],"with":[69,105,128],"redundant":[70],"vocabularies":[71],"by":[72],"assigning":[73],"each":[74],"dimension":[75,116],"a":[77],"specific":[78],"cluster,":[80],"where":[81],"semantically":[82],"similar":[83],"tokens":[84],"are":[85],"grouped":[86],"together.Extensive":[87],"experiments":[88],"demonstrate":[89],"outperforms":[92],"Massive":[97],"Text":[98],"Embedding":[99],"Benchmark":[100],"(MTEB),":[101],"delivering":[102],"compact":[103],"representations":[104],"dimensionality":[106],"comparable":[107],"counterparts.Furthermore,":[110],"inherently":[112],"supports":[113],"efficient":[114],"pruning":[117],"without":[118],"any":[119],"specialized":[120],"objectives":[121],"like":[122],"Matryoshka":[123],"Representation":[124],"Learning.Notably,":[125],"combining":[126],"achieves":[131],"state-of-the-art":[132],"retrieval":[136],"subset":[137],"MTEB":[139],"(i.e.,":[140],"BEIR).":[141],"1":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}