{"id":"https://openalex.org/W2250174865","doi":"https://doi.org/10.18653/v1/d13-1007","title":"A Log-Linear Model for Unsupervised Text Normalization","display_name":"A Log-Linear Model for Unsupervised Text Normalization","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2250174865","doi":"https://doi.org/10.18653/v1/d13-1007","mag":"2250174865"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1007","pdf_url":"https://aclanthology.org/D13-1007.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 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1007.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100657571","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-3021-0522"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9993000030517578,"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":0.9976000189781189,"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/normalization","display_name":"Normalization (sociology)","score":0.8753093481063843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8022801876068115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5434158444404602},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3432983160018921}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8753093481063843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022801876068115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5434158444404602},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3432983160018921},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/d13-1007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1007","pdf_url":"https://aclanthology.org/D13-1007.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 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.6339","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.6339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~jeisenst/papers/yang-emnlp-2013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.6537","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.6537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1007.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1007","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d13-1007","pdf_url":"https://aclanthology.org/D13-1007.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 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1573492157","display_name":"Collaborative Research: Discovering and Exploiting Latent Communities in Social Media","funder_award_id":"1111142","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2250174865.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W9292421","https://openalex.org/W63056884","https://openalex.org/W1631260214","https://openalex.org/W1800296434","https://openalex.org/W1868971014","https://openalex.org/W1909733559","https://openalex.org/W1988827501","https://openalex.org/W1994439916","https://openalex.org/W2016443085","https://openalex.org/W2033444463","https://openalex.org/W2053966956","https://openalex.org/W2055936398","https://openalex.org/W2063276002","https://openalex.org/W2096438711","https://openalex.org/W2100581574","https://openalex.org/W2101200183","https://openalex.org/W2101761627","https://openalex.org/W2112255502","https://openalex.org/W2125270091","https://openalex.org/W2133503566","https://openalex.org/W2137345842","https://openalex.org/W2137807925","https://openalex.org/W2142889507","https://openalex.org/W2144364794","https://openalex.org/W2146867136","https://openalex.org/W2147880316","https://openalex.org/W2152815769","https://openalex.org/W2157765050","https://openalex.org/W2160637503","https://openalex.org/W2163942301","https://openalex.org/W2164107060","https://openalex.org/W2172112754","https://openalex.org/W2252209719","https://openalex.org/W2616657226","https://openalex.org/W3143596294"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2073681303","https://openalex.org/W2359348847","https://openalex.org/W3011538607"],"abstract_inverted_index":{"We":[0,84],"present":[1],"a":[2,20,34,38,65,93,101],"unified":[3],"unsupervised":[4],"statistical":[5],"model":[6,61],"for":[7,55],"text":[8],"normalization.":[9],"The":[10,26],"relation-ship":[11],"between":[12],"standard":[13],"and":[14],"non-standard":[15],"to-kens":[16],"is":[17,62],"characterized":[18],"by":[19],"log-linear":[21],"model,":[22],"permitting":[23],"arbitrary":[24],"features.":[25],"weights":[27],"of":[28,88,96,103],"these":[29],"features":[30],"are":[31],"trained":[32],"in":[33,64],"maximum-likelihood":[35],"framework,":[36],"employing":[37],"novel":[39],"se-quential":[40],"Monte":[41],"Carlo":[42],"training":[43],"algorithm":[44],"to":[45,90],"overcome":[46],"the":[47,72,86],"large":[48,94],"label":[49],"space,":[50],"which":[51,70],"would":[52],"be":[53],"impractical":[54],"traditional":[56],"dynamic":[57],"pro-gramming":[58],"solutions.":[59],"This":[60],"im-plemented":[63],"normalization":[66,78],"system":[67],"called":[68],"UNLOL,":[69],"achieves":[71],"best":[73],"known":[74],"re-sults":[75],"on":[76],"two":[77],"datasets,":[79],"outper-forming":[80],"more":[81],"complex":[82],"systems.":[83],"use":[85],"output":[87],"UNLOL":[89],"automatically":[91],"normalize":[92],"corpus":[95],"social":[97],"media":[98],"text,":[99],"revealing":[100],"set":[102],"coherent":[104],"orthographic":[105],"styles":[106],"that":[107],"under-lie":[108],"online":[109],"language":[110],"variation.":[111],"1":[112]},"counts_by_year":[{"year":2026,"cited_by_count":50},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}