{"id":"https://openalex.org/W7161157161","doi":"https://doi.org/10.1109/dcc66757.2026.00046","title":"On the Size of Higher-Order Prefix-Free Parse Representations","display_name":"On the Size of Higher-Order Prefix-Free Parse Representations","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7161157161","doi":"https://doi.org/10.1109/dcc66757.2026.00046"},"language":null,"primary_location":{"id":"doi:10.1109/dcc66757.2026.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","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/A5136147416","display_name":"Md Helal Hossen","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Md Helal Hossen","raw_affiliation_strings":["University of Texas at Dallas,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026282036","display_name":"Daniel Gibney","orcid":"https://orcid.org/0000-0003-1493-5432"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gibney","raw_affiliation_strings":["University of Texas at Dallas,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5136147416"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95158387,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5875999927520752,"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":0.5875999927520752,"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/T11269","display_name":"Algorithms and Data Compression","score":0.1590999960899353,"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/T11567","display_name":"semigroups and automata theory","score":0.07540000230073929,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/parsing","display_name":"Parsing","score":0.4318000078201294},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.32269999384880066},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24940000474452972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5587000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.498199999332428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.492900013923645},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24940000474452972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2305999994277954},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.22699999809265137}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dcc66757.2026.00046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.45368584990501404}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prefix-Free":[0],"Parsing":[1],"(PFP)":[2],"enables":[3],"efficient":[4],"indexing":[5,59],"of":[6,13,27,39,52,65,82,93,104,108,118,121,128,131,138,143,174,200],"repetitive":[7],"text":[8],"collections":[9],"through":[10],"dictionary-based":[11],"storage":[12],"distinct":[14],"factors":[15,36],"and":[16,135,181,202,214,221],"the":[17,22,45,63,66,80,83,105,126,129,132,136,141,171,175,182,257,280],"corresponding":[18,203],"factor":[19],"positions":[20],"in":[21,78,140],"text.":[23],"The":[24],"parsing":[25,163],"method":[26],"PFP":[28,53,76,85,117,220,232,259],"differs":[29],"from":[30],"LZ78":[31,251,281],"compression":[32],"as":[33,62],"it":[34,55],"separates":[35],"at":[37,148,178,187],"occurrences":[38],"predefined":[40],"trigger":[41,204,238],"strings,":[42],"ensuring":[43],"that":[44,114,160,206,230,234,256],"parse":[46,81,133,184],"is":[47,86,164,242,252],"prefix-free.":[48],"This":[49,254],"prefix-free":[50,94,110,162],"property":[51],"makes":[54],"suitable":[56],"for":[57,115,247],"compressed":[58,88],"applications":[60],"such":[61],"construction":[64],"Burrows-Wheeler":[67],"Transform.":[68],"Recent":[69],"work":[70],"has":[71],"also":[72,196],"introduced":[73],"a":[74,101,116,119,198,215,267],"recursive":[75],"technique,":[77],"which":[79],"initial":[84],"further":[87],"with":[89,236],"an":[90],"additional":[91],"round":[92],"parsing.":[95],"In":[96],"this":[97,156,208],"paper,":[98],"we":[99,228],"provide":[100,197],"theoretical":[102],"analysis":[103],"minimal":[106],"size":[107,173,260],"any":[109],"parse.":[111],"We":[112,154,195],"show":[113],"string":[120,134,239],"length":[122],"<tex":[123,150,167,189,273],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,151,168,190,274],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$n$</tex>,":[125],"sum":[127],"lengths":[130],"number":[137],"nodes":[139],"trie":[142],"dictionary":[144,176],"strings":[145,201,205,249],"must":[146,185],"be":[147,186,262,265],"least":[149,188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2":[152],"\\sqrt{n}$</tex>.":[153],"generalize":[155],"result":[157],"by":[158],"demonstrating":[159,211],"if":[161],"applied":[165],"recursively":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$k$</tex>":[169],"times,":[170],"combined":[172],"tries":[177],"each":[179],"level":[180],"final":[183],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(k+1)":[191],"\\cdot":[192],"n^{1":[193],"/(k+1)}$</tex>.":[194],"family":[199],"achieve":[207],"lower":[209],"bound,":[210],"its":[212],"tightness":[213],"polynomially":[216,270],"large":[217],"separation":[218],"between":[219],"several":[222],"other":[223],"popular":[224],"compressibility":[225],"measures.":[226],"Finally,":[227],"illustrate":[229],"optimal":[231,237,258],"-":[233,241],"is,":[235],"selection":[240],"robust":[243],"against":[244],"one-bit":[245],"catastrophes":[246],"some":[248],"where":[250],"not.":[253],"demonstrates":[255],"cannot":[261],"guaranteed":[263],"to":[264,279],"within":[266],"multiplicative":[268],"ratio":[269],"smaller":[271],"than":[272],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$n^{1":[275],"/":[276],"8}$</tex>":[277],"relative":[278],"size.":[282]},"counts_by_year":[],"updated_date":"2026-05-16T06:04:12.930555","created_date":"2026-05-15T00:00:00"}
