{"id":"https://openalex.org/W2740401134","doi":"https://doi.org/10.18653/v1/p17-2095","title":"Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging","display_name":"Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740401134","doi":"https://doi.org/10.18653/v1/p17-2095","mag":"2740401134"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-2095","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2095","pdf_url":"https://www.aclweb.org/anthology/P17-2095.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-2095.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042954793","display_name":"Hassan Sajjad","orcid":"https://orcid.org/0000-0002-8584-6595"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hassan Sajjad","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002245931","display_name":"Fahim Dalvi","orcid":"https://orcid.org/0000-0003-1183-7837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fahim Dalvi","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689067","display_name":"Nadir Durrani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nadir Durrani","raw_affiliation_strings":["Hamad Bin Khalifa University#TAB#"],"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University#TAB#","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047182137","display_name":"Ahmed Abdelal\u00ed","orcid":"https://orcid.org/0000-0002-4160-8181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA","Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA 02139, USA","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064572063","display_name":"Stephan Vogel","orcid":"https://orcid.org/0000-0003-2630-4881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Vogel","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042954793"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2847,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90986577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"607"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.8427988290786743},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7783259749412537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7070937156677246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6879222393035889},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.644382655620575},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5695171356201172},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5677472949028015},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5666455626487732},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5592674612998962},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5433656573295593},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.5419538617134094},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.48457491397857666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46074405312538147},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.42882007360458374},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4203665256500244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.416761189699173},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.32009071111679077},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10870647430419922},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06592485308647156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8427988290786743},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7783259749412537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7070937156677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6879222393035889},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.644382655620575},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5695171356201172},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5677472949028015},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5666455626487732},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5592674612998962},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5433656573295593},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5419538617134094},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.48457491397857666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46074405312538147},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.42882007360458374},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4203665256500244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.416761189699173},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.32009071111679077},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10870647430419922},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06592485308647156},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p17-2095","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2095","pdf_url":"https://www.aclweb.org/anthology/P17-2095.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1709.00616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.00616","pdf_url":"https://arxiv.org/pdf/1709.00616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2740401134","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1709.00616.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1709.00616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1709.00616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-2095","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-2095","pdf_url":"https://www.aclweb.org/anthology/P17-2095.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 55th Annual Meeting of the Association for\n          Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319188","display_name":"Hamad Bin Khalifa University","ror":"https://ror.org/03eyq4y97"},{"id":"https://openalex.org/F4320334266","display_name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740401134.pdf","grobid_xml":"https://content.openalex.org/works/W2740401134.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W201346080","https://openalex.org/W1905522558","https://openalex.org/W1938755728","https://openalex.org/W2048978997","https://openalex.org/W2097532276","https://openalex.org/W2098603082","https://openalex.org/W2100976324","https://openalex.org/W2116512888","https://openalex.org/W2117717100","https://openalex.org/W2119202242","https://openalex.org/W2135161317","https://openalex.org/W2135843243","https://openalex.org/W2145617667","https://openalex.org/W2147880316","https://openalex.org/W2184135559","https://openalex.org/W2220350356","https://openalex.org/W2250732891","https://openalex.org/W2250816155","https://openalex.org/W2292633562","https://openalex.org/W2413534664","https://openalex.org/W2471147443","https://openalex.org/W2522065177","https://openalex.org/W2525778437","https://openalex.org/W2556053680","https://openalex.org/W2573043117","https://openalex.org/W2573197213","https://openalex.org/W2605717780","https://openalex.org/W2962784628"],"related_works":["https://openalex.org/W2962724530","https://openalex.org/W2962784628","https://openalex.org/W2964308564","https://openalex.org/W2064675550","https://openalex.org/W3204406378","https://openalex.org/W2525778437","https://openalex.org/W2471147443","https://openalex.org/W2980433540","https://openalex.org/W2605717780","https://openalex.org/W2529836050","https://openalex.org/W2524084036","https://openalex.org/W2184135559","https://openalex.org/W2008496475","https://openalex.org/W2909792778","https://openalex.org/W138635755","https://openalex.org/W3157760039","https://openalex.org/W3102259066","https://openalex.org/W2787724617","https://openalex.org/W2119134282","https://openalex.org/W3211815492"],"abstract_inverted_index":{"Hassan":[0],"Sajjad,":[1],"Fahim":[2],"Dalvi,":[3],"Nadir":[4],"Durrani,":[5],"Ahmed":[6],"Abdelali,":[7],"Yonatan":[8],"Belinkov,":[9],"Stephan":[10],"Vogel.":[11],"Proceedings":[12],"of":[13,18],"the":[14,19],"55th":[15],"Annual":[16],"Meeting":[17],"Association":[20],"for":[21],"Computational":[22],"Linguistics":[23],"(Volume":[24],"2:":[25],"Short":[26],"Papers).":[27],"2017.":[28]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
