{"id":"https://openalex.org/W4401687104","doi":"https://doi.org/10.1109/isit57864.2024.10619368","title":"TexShape: Information Theoretic Sentence Embedding for Language Models","display_name":"TexShape: Information Theoretic Sentence Embedding for Language Models","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4401687104","doi":"https://doi.org/10.1109/isit57864.2024.10619368"},"language":"en","primary_location":{"id":"doi:10.1109/isit57864.2024.10619368","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isit57864.2024.10619368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104343609","display_name":"Kaan Kale","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaan Kale","raw_affiliation_strings":["Boğaziçi University,Istanbul,Türkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boğaziçi University,Istanbul,Türkiye","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010743882","display_name":"Homa Esfahanizadeh","orcid":"https://orcid.org/0000-0003-1217-692X"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Homa Esfahanizadeh","raw_affiliation_strings":["Nokia Bell Labs,Murray Hill,NJ,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs,Murray Hill,NJ,USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084231357","display_name":"Noel Elias","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noel Elias","raw_affiliation_strings":["University of Texas at Austin,Austin,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022814373","display_name":"O\u011fuzhan Ba\u015fer","orcid":"https://orcid.org/0009-0004-6314-9627"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oguzhan Baser","raw_affiliation_strings":["University of Texas at Austin,Austin,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075370174","display_name":"Muriel M\u00e9dard","orcid":"https://orcid.org/0000-0003-4059-407X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muriel M\u00e9dard","raw_affiliation_strings":["Massachusetts Institute of Technology (MIT),Cambridge,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology (MIT),Cambridge,USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088120102","display_name":"Sriram Vishwanath","orcid":"https://orcid.org/0000-0003-3112-4885"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Vishwanath","raw_affiliation_strings":["University of Texas at Austin,Austin,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53015458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2038","last_page":"2043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9922999739646912,"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":0.9922999739646912,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9527000188827515,"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":0.7533174753189087},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6042869091033936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5687147974967957},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5569865703582764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4712424874305725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533174753189087},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6042869091033936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5687147974967957},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5569865703582764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4712424874305725}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit57864.2024.10619368","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/isit57864.2024.10619368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W595252221","https://openalex.org/W1490960179","https://openalex.org/W1995875735","https://openalex.org/W2092939357","https://openalex.org/W2137983211","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2725155646","https://openalex.org/W2896457183","https://openalex.org/W2963412800","https://openalex.org/W2963546708","https://openalex.org/W3016473712","https://openalex.org/W3101544782","https://openalex.org/W3189092450","https://openalex.org/W4205807230","https://openalex.org/W4224308101","https://openalex.org/W4238634189","https://openalex.org/W4243316134","https://openalex.org/W4300840296","https://openalex.org/W4322718191","https://openalex.org/W4362515116","https://openalex.org/W4375869185","https://openalex.org/W4388001435","https://openalex.org/W4392903026"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2597655663","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0],"the":[1,8,15,35,51,65,152],"exponential":[2],"growth":[3],"in":[4,14,127,140],"data":[5,39,86],"volume":[6],"and":[7,26,40,96,118,132],"emergence":[9],"of":[10,17,38,53,61,68,142,145],"data-intensive":[11],"applications,":[12],"particularly":[13],"field":[16],"machine":[18],"learning,":[19],"concerns":[20],"related":[21],"to":[22,46,76],"resource":[23],"utilization,":[24],"privacy,":[25],"fairness":[27],"have":[28],"become":[29],"paramount.":[30],"This":[31],"paper":[32],"focuses":[33],"on":[34],"textual":[36],"domain":[37],"addresses":[41],"challenges":[42],"regarding":[43],"encoding":[44],"sentences":[45],"their":[47],"optimized":[48],"representations":[49],"through":[50],"lens":[52],"information-theory.":[54],"In":[55,98],"particular,":[56],"we":[57,101],"use":[58],"empirical":[59],"estimates":[60],"mutual":[62,119],"information,":[63,93],"using":[64,151],"Donsker-Varadhan":[66],"definition":[67],"Kullback-Leibler":[69],"divergence.":[70],"Our":[71,122],"approach":[72],"leverages":[73],"this":[74,99],"estimation":[75],"train":[77],"an":[78],"information-theoretic":[79,116],"sentence":[80],"embedding,":[81],"called":[82],"TexShape,":[83],"for":[84,89,107,115],"(task-based)":[85],"compression":[87,117,138],"or":[88],"filtering":[90],"out":[91],"sensitive":[92,134],"enhancing":[94],"privacy":[95],"fairness.":[97],"study,":[100],"employ":[102],"a":[103],"benchmark":[104],"language":[105],"model":[106],"initial":[108],"text":[109],"representation,":[110],"complemented":[111],"by":[112],"neural":[113],"networks":[114],"information":[120,131,135],"estimations.":[121],"experiments":[123],"demonstrate":[124],"significant":[125],"advancements":[126],"preserving":[128],"maximal":[129],"targeted":[130],"minimal":[133],"over":[136],"adverse":[137],"ratios,":[139],"terms":[141],"predictive":[143],"accuracy":[144],"downstream":[146],"models":[147],"that":[148],"are":[149],"trained":[150],"compressed":[153],"data.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}