{"id":"https://openalex.org/W2467343197","doi":null,"title":"Rank and sparsity in language processing","display_name":"Rank and sparsity in language processing","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2467343197","mag":"2467343197"},"language":"en","primary_location":{"id":"pmh:oai:digital.lib.washington.edu:1773/24250","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/24250","pdf_url":"http://hdl.handle.net/1773/24250","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1773/24250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf E","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102886973","display_name":"Maryam Fazel","orcid":"https://orcid.org/0000-0001-5329-4522","observed_orcids":["https://orcid.org/0000-0001-5329-4522"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Fazel","raw_affiliation_strings":["University of Washington ;"],"raw_orcid":"https://orcid.org/0000-0001-5329-4522","affiliations":[{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033912251","display_name":"Brian Hutchinson","orcid":"https://orcid.org/0000-0002-5537-008X","observed_orcids":["https://orcid.org/0000-0002-5537-008X"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Hutchinson","raw_affiliation_strings":["University of Washington ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington ;","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8291000127792358,"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":0.8291000127792358,"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":0.08540000021457672,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.07400000095367432,"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/language-modeling","display_name":"language modeling","score":0.9290000200271606},{"id":"https://openalex.org/keywords/low-rank-models","display_name":"low-rank models","score":0.7609999775886536},{"id":"https://openalex.org/keywords/sparse-modeling","display_name":"sparse models","score":0.8180000185966492},{"id":"https://openalex.org/keywords/low-rank-tensor","display_name":"low-rank tensor","score":0.6359999775886536},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.44999998807907104},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.5149999856948853},{"id":"https://openalex.org/keywords/exceptional-sequences","display_name":"exceptional sequences","score":0.4359999895095825},{"id":"https://openalex.org/keywords/joint-probability-estimation","display_name":"joint probability estimation","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505422234535217},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.7197611927986145},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7079365849494934},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6065831184387207},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5733539462089539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212881565093994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5126115679740906},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5011484622955322},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4647855758666992},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4473530054092407},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3626422584056854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29011040925979614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13203608989715576},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:digital.lib.washington.edu:1773/24250","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/24250","pdf_url":"http://hdl.handle.net/1773/24250","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:2467343197","doi":null,"is_oa":false,"landing_page_url":"https://digital.lib.washington.edu:443/researchworks/handle/1773/24250","pdf_url":null,"source":{"id":"https://openalex.org/S4306478302","display_name":"ProQuest LLC eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"ProQuest LLC eBooks","raw_type":null}],"best_oa_location":{"id":"pmh:oai:digital.lib.washington.edu:1773/24250","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1773/24250","pdf_url":"http://hdl.handle.net/1773/24250","source":{"id":"https://openalex.org/S4306401128","display_name":"ResearchWorks at the University of Washington (University of Washington)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I201448701","host_organization_name":"University of Washington","host_organization_lineage":["https://openalex.org/I201448701"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G6038698723","display_name":null,"funder_award_id":"W911NF-12-C-0014","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2467343197.pdf","grobid_xml":"https://content.openalex.org/works/W2467343197.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1855068118","https://openalex.org/W2000911789","https://openalex.org/W2003753589"],"related_works":["https://openalex.org/W2029867605","https://openalex.org/W2137607319","https://openalex.org/W2408607167","https://openalex.org/W2251441308","https://openalex.org/W1804883388","https://openalex.org/W2109816866","https://openalex.org/W7102533689","https://openalex.org/W4401042331","https://openalex.org/W1534853518","https://openalex.org/W3207058314"],"abstract_inverted_index":{"Language":[0],"modeling":[1,74],"is":[2,27],"one":[3,156],"of":[4,24,33,169,200,227],"many":[5],"problems":[6],"in":[7,19,52,151,207],"language":[8,46,73,182,203],"processing":[9,183],"that":[10,57,75,97,108,131,149],"have":[11],"to":[12,49,62,72,82,105,137,177,217,233],"grapple":[13],"with":[14,64,117],"naturally":[15],"high":[16],"ambient":[17],"dimensions.Even":[18],"large":[20],"datasets,":[21],"the":[22,31,84,90,123,138,147,158,167,170,173,186,198],"number":[23,32],"unseen":[25],"sequences":[26,102],"overwhelmingly":[28],"larger":[29],"than":[30],"observed":[34],"ones,":[35],"posing":[36],"clear":[37],"challenges":[38],"for":[39,43,180,191,197,242],"estimation.Although":[40],"existing":[41],"methods":[42],"building":[44],"smooth":[45,83],"models":[47,187,204],"tend":[48],"work":[50],"well":[51,60],"general,":[53],"they":[54],"make":[55],"assumptions":[56,78],"are":[58,205],"not":[59,164,189],"suited":[61],"training":[63],"limited":[65,91],"data.This":[66],"thesis":[67,128],"introduces":[68],"a":[69,115,135,142,154,212,225],"new":[70,202],"approach":[71],"makes":[76],"different":[77],"about":[79],"how":[80],"best":[81],"distributions,":[85],"aimed":[86],"at":[87],"better":[88],"handling":[89],"data":[92],"scenario.Among":[93],"these,":[94],"it":[95],"assumes":[96],"some":[98],"words":[99],"and":[100,107,121,239,246],"word":[101],"behave":[103],"similarly":[104],"others":[106],"similarities":[109],"can":[110,221],"be":[111,178,222],"learned":[112],"by":[113],"parameterizing":[114],"model":[116],"matrices":[118],"or":[119,125],"tensors":[120],"controlling":[122],"matrix":[124],"tensor":[126,216],"rank.This":[127],"also":[129],"demonstrates":[130],"sparsity":[132],"acts":[133],"as":[134,195,224],"complement":[136],"low":[139,143,214],"rank":[140,144,215],"parameters:":[141],"component":[145,163],"learns":[146],"regularities":[148],"exist":[150],"language,":[152],"while":[153],"sparse":[155,162],"captures":[157],"exceptional":[159,244],"sequence":[160],"phenomena.The":[161],"only":[165,190],"improves":[166],"quality":[168],"model,":[171],"but":[172,194],"exceptions":[174],"identified":[175],"prove":[176],"meaningful":[179],"other":[181],"tasks,":[184],"making":[185],"useful":[188],"computing":[192],"probabilities":[193],"tools":[196],"analysis":[199],"language.Three":[201],"introduced":[206],"this":[208],"thesis.The":[209],"first":[210],"uses":[211],"factored":[213],"encode":[218],"joint":[219],"probabilities.It":[220],"interpreted":[223],"\"mixture":[226],"unigrams\"":[228],"First,":[229],"I":[230],"would":[231],"like":[232],"thank":[234],"my":[235],"advisors,":[236],"Mari":[237],"Ostendorf":[238],"Maryam":[240],"Fazel,":[241],"their":[243],"guidance":[245],"mentorship.I":[247],"am":[248],"deeply":[249]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-07-22T00:00:00"}