{"id":"https://openalex.org/W4389518396","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.13","title":"Enhancing Arabic Machine Translation for E-commerce Product Information: Data Quality Challenges and Innovative Selection Approaches","display_name":"Enhancing Arabic Machine Translation for E-commerce Product Information: Data Quality Challenges and Innovative Selection Approaches","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518396","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.13"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.13","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.13","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.arabicnlp-1.13","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.13.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 ArabicNLP 2023","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/2023.arabicnlp-1.13.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005337426","display_name":"Bryan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109663426","display_name":"Salah Danial","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salah Danial","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Stephan Walter","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Walter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3541,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56741212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.9945999979972839,"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/T10759","display_name":"Translation Studies and Practices","score":0.002899999963119626,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00139999995008111,"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-machine-translation","display_name":"Arabic machine translation","score":0.996999979019165},{"id":"https://openalex.org/keywords/training-data-quality","display_name":"training data quality","score":0.8629999756813049},{"id":"https://openalex.org/keywords/dataset-selection","display_name":"data selection","score":0.8109999895095825},{"id":"https://openalex.org/keywords/english-arabic-translation","display_name":"English-Arabic translation","score":0.8450000286102295},{"id":"https://openalex.org/keywords/data-validation","display_name":"data validation","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545226812362671},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6756647229194641},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6346709132194519},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.608801007270813},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5820971727371216},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5235174298286438},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4989776611328125},{"id":"https://openalex.org/C78597825","wikidata":"https://www.wikidata.org/wiki/Q484847","display_name":"E-commerce","level":2,"score":0.48513326048851013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44193264842033386},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4264333248138428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39651811122894287},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34745559096336365},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33771204948425293},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20345917344093323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11303991079330444},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10469335317611694},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.arabicnlp-1.13","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.13","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.arabicnlp-1.13","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.13.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 ArabicNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.13","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.13","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.arabicnlp-1.13","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.13.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 ArabicNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518396.pdf","grobid_xml":"https://content.openalex.org/works/W4389518396.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2006258004","https://openalex.org/W2061922307","https://openalex.org/W2105767494","https://openalex.org/W2147272182","https://openalex.org/W2160131015","https://openalex.org/W2160170318","https://openalex.org/W2185749428","https://openalex.org/W2250342921","https://openalex.org/W2319824271","https://openalex.org/W2468328197","https://openalex.org/W2563351168","https://openalex.org/W2573728411","https://openalex.org/W2626778328","https://openalex.org/W2769096030","https://openalex.org/W2798362442","https://openalex.org/W2885950361","https://openalex.org/W2888070626","https://openalex.org/W2913337508","https://openalex.org/W2963366389","https://openalex.org/W2969696767","https://openalex.org/W3028616679","https://openalex.org/W3035473397","https://openalex.org/W3087105636","https://openalex.org/W3094482246","https://openalex.org/W3180521376","https://openalex.org/W3186689849","https://openalex.org/W3197251449","https://openalex.org/W4254129368","https://openalex.org/W4385574316"],"related_works":["https://openalex.org/W3023523443","https://openalex.org/W4205243694","https://openalex.org/W2804562751","https://openalex.org/W7204003529","https://openalex.org/W4328137701","https://openalex.org/W3185274513","https://openalex.org/W3087105636","https://openalex.org/W2280604321","https://openalex.org/W7054503346","https://openalex.org/W7217517335"],"abstract_inverted_index":{"Product":[0],"information":[1],"in":[2,23,92,103],"e-commerce":[3,24,93],"is":[4,73],"usually":[5],"localized":[6],"using":[7],"machine":[8],"translation":[9],"(MT)":[10],"systems.The":[11],"Arabic":[12,21,90],"language":[13],"has":[14],"rich":[15],"morphology":[16],"and":[17,79,94,108,120],"dialectal":[18],"variations,":[19],"so":[20],"MT":[22,71,91,102,115],"training":[25,57,83],"requires":[26],"a":[27,65],"larger":[28],"volume":[29],"of":[30,40,56,70,81],"data":[31,34,43,58,97,110],"from":[32],"diverse":[33],"sources;":[35],"Given":[36],"the":[37,51,54,68,77,82,89,96],"dynamic":[38],"nature":[39],"e-commerce,":[41],"such":[42],"needs":[44],"to":[45,49,113,132],"be":[46],"acquired":[47],"periodically":[48,59],"update":[50],"MT.Consequently,":[52],"validating":[53],"quality":[55,78,98],"within":[60],"an":[61],"industrial":[62],"setting":[63],"presents":[64],"notable":[66],"challenge.Meanwhile,":[67],"performance":[69],"systems":[72],"significantly":[74],"impacted":[75],"by":[76],"appropriateness":[80],"data.Hence,":[84],"this":[85],"study":[86],"first":[87],"examines":[88],"investigates":[95],"challenges":[99],"for":[100,116,136],"English-Arabic":[101],"ecommerce":[104],"then":[105],"proposes":[106],"heuristics-based":[107],"topic-based":[109],"selection":[111],"approaches":[112,128],"improve":[114],"product":[117],"information.Both":[118],"online":[119],"offline":[121],"experiment":[122],"results":[123],"have":[124],"shown":[125],"our":[126],"proposed":[127],"are":[129],"effective,":[130],"leading":[131],"improved":[133],"shopping":[134],"experiences":[135],"customers.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2023-12-10T00:00:00"}
