{"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","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2034","pdf_url":"https://doi.org/10.3115/v1/p14-2034","source":null,"license":null,"license_id":null,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/p14-2034","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001666093","display_name":"Will Monroe","orcid":"https://orcid.org/0000-0001-9986-5079"},"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":true,"raw_author_name":"Will Monroe","raw_affiliation_strings":["Stanford University ()"],"affiliations":[{"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},"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":["Stanford University ()"],"affiliations":[{"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"},"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":["Stanford University ()"],"affiliations":[{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001666093"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":13.9542,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98898707,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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":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":"Natural Language Processing Techniques","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":"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/T13629","display_name":"Text Readability and Simplification","score":0.9923999905586243,"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/arabic","display_name":"Arabic","score":0.7781224250793457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423157095909119},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6963244676589966},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6610022187232971},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6318802833557129},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6164006590843201},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5744579434394836},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5033363699913025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4757675528526306},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4367198646068573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3633183538913727},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2797160744667053},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09555462002754211},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07384628057479858}],"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","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2034","pdf_url":"https://doi.org/10.3115/v1/p14-2034","source":null,"license":null,"license_id":null,"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","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","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","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2034","pdf_url":"https://doi.org/10.3115/v1/p14-2034","source":null,"license":null,"license_id":null,"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":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"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/W4376166954","https://openalex.org/W2152148513","https://openalex.org/W4281397339","https://openalex.org/W4301311969","https://openalex.org/W4286909598","https://openalex.org/W4312910505","https://openalex.org/W2357339972","https://openalex.org/W2783380393","https://openalex.org/W2280198878","https://openalex.org/W2951876757"],"abstract_inverted_index":{"Segmentation":[0],"of":[1,12],"clitics":[2],"has":[3],"been":[4],"shown":[5],"to":[6,24,67,100,103],"improve":[7],"accuracy":[8],"on":[9,31,41,82,93],"a":[10,57,94],"variety":[11],"Arabic":[13,32,72,98],"NLP":[14],"tasks.":[15],"However,":[16],"state-of-the-art":[17],"Ara-bic":[18],"word":[19],"segmenters":[20],"are":[21],"either":[22],"limited":[23],"formal":[25],"Modern":[26],"Standard":[27],"Arabic,":[28],"perform-ing":[29],"poorly":[30],"text":[33],"featuring":[34],"dialectal":[35,71],"vocabulary":[36],"and":[37,62,70,86],"grammar,":[38],"or":[39],"rely":[40],"lin-guistic":[42],"knowledge":[43],"that":[44,76],"is":[45],"hand-tuned":[46],"for":[47,106,111],"each":[48],"dialect.":[49],"We":[50],"extend":[51],"an":[52],"existing":[53,80],"MSA":[54],"segmenter":[55,108],"with":[56],"simple":[58],"domain":[59],"adapta-tion":[60],"technique":[61],"new":[63],"features":[64],"in":[65],"order":[66],"segment":[68],"informal":[69],"text.":[73],"Experiments":[74],"show":[75],"our":[77],"system":[78],"outperforms":[79],"systems":[81],"newswire,":[83],"broadcast":[84],"news":[85],"Egyptian":[87,97,112],"dialect,":[88],"im-proving":[89],"segmentation":[90],"F1":[91],"score":[92],"recently":[95],"released":[96],"corpus":[99],"95.1%,":[101],"compared":[102],"90.8":[104],"%":[105],"another":[107],"designed":[109],"specifically":[110],"Arabic.":[113],"1":[114]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}