{"id":"https://openalex.org/W2160538511","doi":"https://doi.org/10.3115/1220175.1220176","title":"Combination of Arabic preprocessing schemes for statistical machine translation","display_name":"Combination of Arabic preprocessing schemes for statistical machine translation","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2160538511","doi":"https://doi.org/10.3115/1220175.1220176","mag":"2160538511"},"language":"en","primary_location":{"id":"doi:10.3115/1220175.1220176","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220176","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220176&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1220176&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030866856","display_name":"Fatiha Sadat","orcid":"https://orcid.org/0000-0002-9292-722X"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Fatiha Sadat","raw_affiliation_strings":["National Research Council of Canada"],"affiliations":[{"raw_affiliation_string":"National Research Council of Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030866856"],"corresponding_institution_ids":["https://openalex.org/I4210159778"],"apc_list":null,"apc_paid":null,"fwci":9.7694,"has_fulltext":true,"cited_by_count":84,"citation_normalized_percentile":{"value":0.98017446,"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":"1","last_page":"8"},"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":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9789999723434448,"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/machine-translation","display_name":"Machine translation","score":0.8704351782798767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8251911401748657},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7990105152130127},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6911709308624268},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6705989837646484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6489450931549072},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.6035435199737549},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5954427123069763},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5281445980072021},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5267252922058105},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5138409733772278},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.47853049635887146},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.45764845609664917},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.41928985714912415},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41461044549942017},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41446322202682495},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4113558530807495},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1105671226978302},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07258564233779907}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8704351782798767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251911401748657},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7990105152130127},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6911709308624268},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6705989837646484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6489450931549072},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.6035435199737549},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5954427123069763},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5281445980072021},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5267252922058105},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5138409733772278},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.47853049635887146},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.45764845609664917},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.41928985714912415},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41461044549942017},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41446322202682495},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4113558530807495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1105671226978302},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07258564233779907},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/1220175.1220176","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220176","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220176&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:8913505","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=21a83ebf-dbc5-49f6-9613-e92b3ecd276a","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=21a83ebf-dbc5-49f6-9613-e92b3ecd276a","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.93.6769","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.93.6769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://iit-iti.nrc-cnrc.gc.ca/iit-publications-iti/docs/NRC-48757.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1220175.1220176","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1220175.1220176","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1220176&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL  - ACL '06","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3190074090","display_name":null,"funder_award_id":"HR0011-06-C-0023","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"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/W2160538511.pdf","grobid_xml":"https://content.openalex.org/works/W2160538511.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W146914567","https://openalex.org/W201231365","https://openalex.org/W222053410","https://openalex.org/W1483849869","https://openalex.org/W1489525520","https://openalex.org/W1498238796","https://openalex.org/W1631260214","https://openalex.org/W1998301456","https://openalex.org/W2017802499","https://openalex.org/W2048978997","https://openalex.org/W2100976324","https://openalex.org/W2101105183","https://openalex.org/W2104027215","https://openalex.org/W2132248251","https://openalex.org/W2135161317","https://openalex.org/W2146574666","https://openalex.org/W2163296342","https://openalex.org/W2170464899","https://openalex.org/W2172144952","https://openalex.org/W2294624586","https://openalex.org/W2403096031","https://openalex.org/W2971932245","https://openalex.org/W4242105955","https://openalex.org/W7018160392"],"related_works":["https://openalex.org/W3204448004","https://openalex.org/W2122287718","https://openalex.org/W2740094425","https://openalex.org/W2753600765","https://openalex.org/W2587602790","https://openalex.org/W2566847733","https://openalex.org/W193726211","https://openalex.org/W3196981096","https://openalex.org/W2109153187","https://openalex.org/W2585971314"],"abstract_inverted_index":{"Statistical":[0],"machine":[1,40,74],"translation":[2,90],"is":[3,27,43],"quite":[4],"robust":[5],"when":[6],"it":[7],"comes":[8],"to":[9],"the":[10,59,69],"choice":[11],"of":[12,31,61,71],"input":[13],"representation.":[14],"It":[15],"only":[16],"requires":[17],"consistency":[18],"between":[19],"training":[20],"and":[21,79],"testing.":[22],"As":[23],"a":[24,28],"result,":[25],"there":[26],"wide":[29],"range":[30],"possible":[32],"preprocessing":[33,64,85],"choices":[34],"for":[35,47,66,83],"data":[36],"used":[37],"in":[38,88],"statistical":[39,73],"translation.":[41,75],"This":[42],"even":[44],"more":[45],"so":[46],"morphologically":[48],"rich":[49],"languages":[50],"such":[51],"as":[52],"Arabic.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"study":[58],"effect":[60],"different":[62,81],"word-level":[63],"schemes":[65,86],"Arabic":[67],"on":[68],"quality":[70],"phrase-based":[72],"We":[76],"also":[77],"present":[78],"evaluate":[80],"methods":[82],"combining":[84],"resulting":[87],"improved":[89],"quality.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}