{"id":"https://openalex.org/W6966355354","doi":"https://doi.org/10.3929/ethz-b-000716646","title":"Algorithms for Decoding Probabilistic Language Generators: Beam Search and Locally Typical Sampling","display_name":"Algorithms for Decoding Probabilistic Language Generators: Beam Search and Locally Typical Sampling","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6966355354","doi":"https://doi.org/10.3929/ethz-b-000716646"},"language":"en","primary_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/716646","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/716646","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/716646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Meister, Clara Isabel","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Meister, Clara Isabel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6585000157356262,"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":0.6585000157356262,"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/T12031","display_name":"Speech and dialogue systems","score":0.12759999930858612,"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":0.08089999854564667,"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/beam-search","display_name":"Beam search","score":0.7105000019073486},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.647599995136261},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.629800021648407},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5458999872207642},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45419999957084656},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.40639999508857727},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4041999876499176},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40070000290870667},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.7105000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965000033378601},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.647599995136261},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.629800021648407},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5458999872207642},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.36489999294281006},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/716646","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/716646","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"doi:10.3929/ethz-b-000716646","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000716646","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/716646","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/716646","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7780224084854126,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Natural":[0],"language":[1,16,54,361,390],"generation":[2,86,219,262],"(NLG)":[3],"systems":[4],"overwhelmingly":[5],"rely":[6],"on":[7],"probabilistic":[8,82,360,389],"models":[9,22,83],"to":[10,46,51,71,116,133,140,150,168,238,325,334,351,365,386],"approximate":[11],"task-specific":[12],"distributions":[13,30],"over":[14,31],"natural":[15,53],"strings.":[17,55],"The":[18,372],"majority":[19],"of":[20,110,144,160,189,256,263,270,286,297,311,321],"these":[21,287],"are":[23,363],"auto-regressive":[24],"and":[25,93,108,174,200,232,266,295,381],"locally":[26],"normalized,":[27],"producing":[28],"probability":[29,68],"the":[32,41,66,77,180,194,261,268,277,284,292,308,319,356],"next":[33,215],"token":[34],"given":[35],"prior":[36],"context.":[37],"At":[38],"inference":[39],"time,":[40],"user":[42],"must":[43],"decide":[44],"how":[45,217,233],"use":[47,315],"such":[48,72],"a":[49,59,185,228,247,253,301,327],"distribution":[50],"generate":[52],"Beam":[56],"search":[57,223,299],"is":[58,138,332],"widely":[60],"used":[61],"approximation":[62],"algorithm":[63,195,303,349],"for":[64,80,240,274,283,304,379],"finding":[65],"highest":[67],"string":[69],"according":[70],"distributions.":[73],"It":[74],"has":[75],"been":[76],"go-to":[78],"tool":[79],"decoding":[81,302,323,329,370],"in":[84,103,128,221,246,290,342,383],"numerous":[85],"tasks,":[87],"e.g.,":[88],"machine":[89],"translation,":[90],"abstractive":[91],"summarization":[92],"constrained":[94],"decoding.":[95],"Yet":[96],"at":[97],"times,":[98],"it":[99],"exhibits":[100],"notable":[101],"variability":[102],"output":[104],"quality,":[105],"computational":[106,207],"inefficiency,":[107,165],"lack":[109],"diversity.":[111],"This":[112],"thesis":[113],"first":[114,181],"aims":[115],"better":[117,388],"understand":[118],"beam":[119,129,162,190,222,257,298],"search's":[120],"success.":[121],"We":[122,155,214,250,279,345],"identify":[123],"an":[124,197],"inductive":[125],"bias":[126],"inherent":[127],"search,":[130,191,258],"leading":[131],"us":[132,237],"propose":[134,326],"that":[135,331,337,347,359],"its":[136,141,164,166,175],"success":[137],"due":[139],"implicit":[142],"enforcement":[143],"uniform":[145],"information":[146,339],"density---a":[147],"property":[148],"linked":[149],"psycholinguistic":[151],"theories---in":[152],"generated":[153],"text.":[154],"then":[156],"address":[157,179],"three":[158],"limitations":[159],"standard":[161],"search:":[163],"tendency":[167],"produce":[169,335,367],"sets":[170],"with":[171],"low":[172],"diversity,":[173,294],"deterministic":[176],"nature.":[177],"To":[178],"limitation,":[182],"we":[183,314],"introduce":[184],"more":[186],"efficient":[187],"variant":[188],"which":[192,259],"frames":[193],"as":[196,227,244,300],"agenda-based":[198],"process":[199],"employs":[201],"best-first":[202],"prioritization;":[203],"this":[204,234,312,348],"approach":[205],"reduces":[206],"cost":[208],"by":[209],"eliminating":[210],"unnecessary":[211],"path":[212],"exploration.":[213],"show":[216],"each":[218],"step":[220],"can":[224],"be":[225],"formulated":[226],"subdeterminant":[229],"maximization":[230],"problem,":[231],"framing":[235],"allows":[236],"optimize":[239],"set-level":[241],"characteristics":[242],"(such":[243],"diversity)":[245],"principled":[248],"fashion.":[249],"further":[251],"develop":[252],"stochastic":[254],"generalization":[255],"facilitates":[260],"diverse":[264],"samples":[265],"enables":[267],"construction":[269],"statistically":[271],"consistent":[272],"estimators":[273],"expectations":[275],"under":[276,368],"model.":[278],"provide":[280],"empirical":[281],"evidence":[282],"effectiveness":[285],"new":[288,328],"techniques":[289],"improving":[291],"efficiency,":[293],"adaptability":[296],"NLG":[305],"tasks.":[306],"In":[307],"last":[309],"part":[310],"thesis,":[313],"our":[316],"insights":[317],"about":[318],"properties":[320],"effective":[322],"strategies":[324],"algorithm---one":[330],"designed":[333],"text":[336],"mimics":[338],"content":[340],"patterns":[341],"human":[343],"communication.":[344],"observe":[346],"leads":[350],"high-quality":[352],"text,":[353],"consistently":[354],"reducing":[355],"degenerate":[357],"repetitions":[358],"generators":[362],"known":[364],"occasionally":[366],"other":[369],"strategies.":[371],"methods":[373],"proposed":[374],"herein":[375],"offer":[376],"valuable":[377],"tools":[378],"researchers":[380],"practitioners":[382],"their":[384],"effort":[385],"create":[387],"generators.":[391]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}