{"id":"https://openalex.org/W2517729625","doi":"https://doi.org/10.18653/v1/p16-2023","title":"Improving cross-domain n-gram language modelling with skipgrams","display_name":"Improving cross-domain n-gram language modelling with skipgrams","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2517729625","doi":"https://doi.org/10.18653/v1/p16-2023","mag":"2517729625"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2023","pdf_url":"https://www.aclweb.org/anthology/P16-2023.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/P16-2023.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060360602","display_name":"Louis Onrust","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Louis Onrust","raw_affiliation_strings":["Radboud University Nijmegen"],"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031562992","display_name":"Antal van den Bosch","orcid":"https://orcid.org/0000-0003-2493-656X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antal van den Bosch","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.113,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.588495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":83},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"142"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Statistical Machine Translation and Natural Language Processing","score":1.0,"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":"Statistical Machine Translation and Natural Language Processing","score":1.0,"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":"Natural Language Processing","score":0.9998,"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/T13629","display_name":"Automatic Text Simplification and Readability Assessment","score":0.9975,"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":0.9785893},{"id":"https://openalex.org/keywords/language-modeling","display_name":"Language Modeling","score":0.535865},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5142238},{"id":"https://openalex.org/keywords/lexical-simplification","display_name":"Lexical Simplification","score":0.511595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural Language Processing","score":0.509382},{"id":"https://openalex.org/keywords/statistical-language-models","display_name":"Statistical Language Models","score":0.506359},{"id":"https://openalex.org/keywords/flemish","display_name":"Flemish","score":0.50531226},{"id":"https://openalex.org/keywords/semantic-simplification","display_name":"Semantic Simplification","score":0.503449}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9785893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7996013},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6647127},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.65738785},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6074292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5248064},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5142238},{"id":"https://openalex.org/C2776802314","wikidata":"https://www.wikidata.org/wiki/Q34147","display_name":"Flemish","level":2,"score":0.50531226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48624578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46308547},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08571097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06979939},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2023","pdf_url":"https://www.aclweb.org/anthology/P16-2023.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/603080","pdf_url":"https://lirias.kuleuven.be/bitstream/123456789/603080/1/4254_final.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":["KU Leuven"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/159825","pdf_url":"https://repository.ubn.ru.nl/bitstream/handle/2066/159825/1/159825.pdf","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":["Royal Netherlands Academy of Arts and Sciences"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/159825/159825.pdf","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/159825/159825.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":["Radboud University Nijmegen"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2023","pdf_url":"https://www.aclweb.org/anthology/P16-2023.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W113586804","https://openalex.org/W1625582487","https://openalex.org/W1631260214","https://openalex.org/W1934041838","https://openalex.org/W2063390378","https://openalex.org/W2106433837","https://openalex.org/W2111305191","https://openalex.org/W2132957691","https://openalex.org/W2154099718","https://openalex.org/W2165814974","https://openalex.org/W2168664213","https://openalex.org/W2558433961","https://openalex.org/W2611669587","https://openalex.org/W2882319491","https://openalex.org/W29952999","https://openalex.org/W635530177"],"related_works":["https://openalex.org/W4322096525","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2787311093","https://openalex.org/W2551914602","https://openalex.org/W2252095989","https://openalex.org/W2169518243","https://openalex.org/W2132221452","https://openalex.org/W2105076537","https://openalex.org/W1577263324"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"improve":[4],"over":[5],"the":[6,28],"hierarchical":[7],"Pitman-Yor":[8],"processes":[9],"language":[10,70],"model":[11],"in":[12,65,67,78],"a":[13,39,62,68,79],"cross-domain":[14,54,69],"setting":[15],"by":[16],"adding":[17,24],"skipgrams":[18],"as":[19],"features.":[20],"We":[21,47,60],"find":[22,49],"that":[23,50],"skipgram":[25],"features":[26],"reduces":[27],"perplexity.":[29],"This":[30],"reduction":[31,64,77],"is":[32],"substantial":[33],"when":[34],"models":[35],"are":[36],"trained":[37],"on":[38,44],"generic":[40],"corpus":[41],"and":[42,53,73,85],"tested":[43],"domain-specific":[45],"corpora.":[46],"also":[48],"within-domain":[51,80],"testing":[52,55],"require":[56],"different":[57],"backoff":[58],"strategies.":[59],"observe":[61],"30-40%":[63],"perplexity":[66],"modelling":[71],"task,":[72],"up":[74],"to":[75],"6%":[76],"experiment,":[81],"for":[82],"both":[83],"English":[84],"Flemish-Dutch.":[86]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2517729625","counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2024-11-22T19:09:31.324786","created_date":"2016-09-16"}
