{"id":"https://openalex.org/W2250659129","doi":"https://doi.org/10.3115/v1/p14-2034","title":"Word Segmentation of Informal Arabic with Domain Adaptation","display_name":"Word Segmentation of Informal Arabic with Domain Adaptation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250659129","doi":"https://doi.org/10.3115/v1/p14-2034","mag":"2250659129"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2034","doi":"https://doi.org/10.3115/v1/p14-2034","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2034","pdf_url":"https://aclanthology.org/P14-2034.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/P14-2034.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Will Monroe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Will Monroe","raw_affiliation_strings":["Computer Science Department , Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004988074","display_name":"Spence Green","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spence Green","raw_affiliation_strings":["Computer Science Department , Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X","observed_orcids":["https://orcid.org/0000-0001-6155-649X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Computer Science Department , Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":6.671,"has_fulltext":true,"cited_by_count":81,"citation_normalized_percentile":{"value":0.97981689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"206","last_page":"211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/clitics","display_name":"clitics","score":0.5950000286102295},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/egyptian-arabic","display_name":"Egyptian Arabic","score":0.8009999990463257},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.7760000228881836},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.9269999861717224},{"id":"https://openalex.org/keywords/broadcast-news","display_name":"broadcast news","score":0.8759999871253967}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7781224250793457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423157095909119},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6963244676589966},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6610022187232971},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6318802833557129},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6164006590843201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5744579434394836},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5033363699913025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4757675528526306},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4367198646068573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3633183538913727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2797160744667053},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09555462002754211},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07384628057479858},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/p14-2034","doi":"https://doi.org/10.3115/v1/p14-2034","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2034","pdf_url":"https://aclanthology.org/P14-2034.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.451.9144","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.451.9144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.stanford.edu/pubs/monroe-green-manning-acls2014.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.655.3447","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.655.3447","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/P/P14/P14-2034.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2034","doi":"https://doi.org/10.3115/v1/p14-2034","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2034","pdf_url":"https://aclanthology.org/P14-2034.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250659129.pdf","grobid_xml":"https://content.openalex.org/works/W2250659129.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W41492599","https://openalex.org/W1598638450","https://openalex.org/W1957504465","https://openalex.org/W2042783153","https://openalex.org/W2057399676","https://openalex.org/W2113024997","https://openalex.org/W2120354757","https://openalex.org/W2131988669","https://openalex.org/W2132483016","https://openalex.org/W2135161317","https://openalex.org/W2147880316","https://openalex.org/W2149709850","https://openalex.org/W2163238067","https://openalex.org/W2250414785","https://openalex.org/W2250732891"],"related_works":["https://openalex.org/W2970822246","https://openalex.org/W2747566258","https://openalex.org/W2970101452","https://openalex.org/W2614862557","https://openalex.org/W2740130688","https://openalex.org/W2250378459","https://openalex.org/W2097341304","https://openalex.org/W7123362284","https://openalex.org/W6973633513","https://openalex.org/W2575598244"],"abstract_inverted_index":{"Segmentation":[0],"of":[1,12],"clitics":[2],"has":[3],"been":[4],"shown":[5],"to":[6,23,65,97,100],"improve":[7],"accuracy":[8],"on":[9,30,40,79,90],"a":[10,55,91],"variety":[11],"Arabic":[13,17,31,70,95],"NLP":[14],"tasks.However,":[15],"state-of-the-art":[16],"word":[18],"segmenters":[19],"are":[20],"either":[21],"limited":[22],"formal":[24],"Modern":[25],"Standard":[26],"Arabic,":[27],"performing":[28],"poorly":[29],"text":[32],"featuring":[33],"dialectal":[34,69],"vocabulary":[35],"and":[36,60,68,82],"grammar,":[37],"or":[38],"rely":[39],"linguistic":[41],"knowledge":[42],"that":[43,73],"is":[44],"hand-tuned":[45],"for":[46,102,107],"each":[47],"dialect.We":[48],"extend":[49],"an":[50],"existing":[51,77],"MSA":[52],"segmenter":[53,104],"with":[54],"simple":[56],"domain":[57],"adaptation":[58],"technique":[59],"new":[61],"features":[62],"in":[63],"order":[64],"segment":[66],"informal":[67],"text.Experiments":[71],"show":[72],"our":[74],"system":[75],"outperforms":[76],"systems":[78],"broadcast":[80],"news":[81],"Egyptian":[83,94,108],"dialect,":[84],"improving":[85],"segmentation":[86],"F":[87],"1":[88],"score":[89],"recently":[92],"released":[93],"corpus":[96],"92.09%,":[98],"compared":[99],"91.60%":[101],"another":[103],"designed":[105],"specifically":[106],"Arabic.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":4}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2016-06-24T00:00:00"}