{"id":"https://openalex.org/W2511530731","doi":"https://doi.org/10.18653/v1/p16-1083","title":"Normalized Log-Linear Interpolation of Backoff Language Models is Efficient","display_name":"Normalized Log-Linear Interpolation of Backoff Language Models is Efficient","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2511530731","doi":"https://doi.org/10.18653/v1/p16-1083","mag":"2511530731"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1083","pdf_url":"https://www.aclweb.org/anthology/P16-1083.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P16-1083.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070589644","display_name":"Kenneth Heafield","orcid":"https://orcid.org/0000-0002-6344-9927"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Kenneth Heafield","raw_affiliation_strings":["University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090089591","display_name":"Chase Geigle","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Chase Geigle","raw_affiliation_strings":["University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077883199","display_name":"Sean Massung","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sean Massung","raw_affiliation_strings":["University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006314068","display_name":"Lane Schwartz","orcid":"https://orcid.org/0000-0003-2609-8133"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Lane Schwartz","raw_affiliation_strings":["University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh 10 Crichton Street Edinburgh EH8 9AB United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign 707 S. Mathews Ave. Urbana, IL 61801 United States","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"876","last_page":"886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9606000185012817,"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/perplexity","display_name":"Perplexity","score":0.9391953945159912},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.7663552761077881},{"id":"https://openalex.org/keywords/linear-interpolation","display_name":"Linear interpolation","score":0.6393614411354065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5583667159080505},{"id":"https://openalex.org/keywords/trilinear-interpolation","display_name":"Trilinear interpolation","score":0.5043319463729858},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43751460313796997},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.41654258966445923},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3972132205963135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37908071279525757},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32063597440719604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19667893648147583},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.17766204476356506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.11678430438041687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09379991888999939},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05715659260749817}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9391953945159912},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.7663552761077881},{"id":"https://openalex.org/C171836373","wikidata":"https://www.wikidata.org/wiki/Q2266329","display_name":"Linear interpolation","level":3,"score":0.6393614411354065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583667159080505},{"id":"https://openalex.org/C188325010","wikidata":"https://www.wikidata.org/wiki/Q861176","display_name":"Trilinear interpolation","level":4,"score":0.5043319463729858},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43751460313796997},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.41654258966445923},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3972132205963135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37908071279525757},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32063597440719604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19667893648147583},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.17766204476356506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.11678430438041687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09379991888999939},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05715659260749817}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p16-1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1083","pdf_url":"https://www.aclweb.org/anthology/P16-1083.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/cf89f099-ac03-4f25-a33f-ec6f365bec78","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cf89f099-ac03-4f25-a33f-ec6f365bec78","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/p16-1083","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1083","pdf_url":"https://www.aclweb.org/anthology/P16-1083.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2783837403","display_name":null,"funder_award_id":"DGE-1144245","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2511530731.pdf","grobid_xml":"https://content.openalex.org/works/W2511530731.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W22168010","https://openalex.org/W98731357","https://openalex.org/W101576916","https://openalex.org/W111602769","https://openalex.org/W126222424","https://openalex.org/W635530177","https://openalex.org/W932413789","https://openalex.org/W1597533204","https://openalex.org/W1631260214","https://openalex.org/W1934041838","https://openalex.org/W2010416582","https://openalex.org/W2045633041","https://openalex.org/W2096375461","https://openalex.org/W2097927681","https://openalex.org/W2106540279","https://openalex.org/W2115081467","https://openalex.org/W2124807415","https://openalex.org/W2134237567","https://openalex.org/W2134800885","https://openalex.org/W2141440284","https://openalex.org/W2158195707","https://openalex.org/W2171457693","https://openalex.org/W2180952760","https://openalex.org/W2250695194","https://openalex.org/W2251232800","https://openalex.org/W2270190199","https://openalex.org/W2295800168","https://openalex.org/W2512924740","https://openalex.org/W2595715041"],"related_works":["https://openalex.org/W2364365984","https://openalex.org/W2378343395","https://openalex.org/W2389908107","https://openalex.org/W2532653122","https://openalex.org/W2387056800","https://openalex.org/W1978764692","https://openalex.org/W2384877220","https://openalex.org/W2359833404","https://openalex.org/W3157416991","https://openalex.org/W2380422832"],"abstract_inverted_index":{"We":[0,40],"prove":[1],"that":[2,25,73],"log-linearly":[3],"interpolated":[4],"backoff":[5,18],"language":[6],"models":[7],"can":[8,76],"be":[9,77],"efficiently":[10,79],"and":[11,71],"exactly":[12],"collapsed":[13],"into":[14],"a":[15,52,81],"single":[16],"normalized":[17],"model,":[19],"contradicting":[20],"While":[21],"prior":[22],"work":[23],"reported":[24],"log-linear":[26,102],"interpolation":[27,61,91,103],"yields":[28,104],"lower":[29],"perplexity":[30,106],"than":[31],"linear":[32,114],"interpolation,":[33],"normalizing":[34,57],"at":[35],"query":[36],"time":[37],"was":[38],"impractical.":[39],"normalize":[41],"the":[42,56,74],"model":[43],"offline":[44],"in":[45,80,88],"advance,":[46],"which":[47,93],"is":[48,94],"efficient":[49],"due":[50],"to":[51,67,111],"recurrence":[53],"relationship":[54],"between":[55],"factors.":[58],"To":[59],"tune":[60],"weights,":[62],"we":[63],"apply":[64],"Newton's":[65],"method":[66],"this":[68],"convex":[69],"problem":[70],"show":[72],"derivatives":[75],"computed":[78],"batch":[82],"process.":[83],"These":[84],"findings":[85],"are":[86],"combined":[87],"new":[89],"open-source":[90],"tool,":[92],"distributed":[95],"with":[96],"KenLM.":[97],"With":[98],"21":[99],"out-of-domain":[100],"corpora,":[101],"72.58":[105],"on":[107],"TED":[108],"talks,":[109],"compared":[110],"75.91":[112],"for":[113],"interpolation.":[115]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}