{"id":"https://openalex.org/W7140105413","doi":"https://doi.org/10.18653/v1/2026.eacl-long.102","title":"Computational Benchmarks for Egyptian Arabic Child Directed Speech","display_name":"Computational Benchmarks for Egyptian Arabic Child Directed Speech","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140105413","doi":"https://doi.org/10.18653/v1/2026.eacl-long.102"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.102","doi":"https://doi.org/10.18653/v1/2026.eacl-long.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.102","pdf_url":"https://aclanthology.org/2026.eacl-long.102.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long 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/2026.eacl-long.102.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019390269","display_name":"Salam Khalifa","orcid":"https://orcid.org/0000-0003-0049-3637","observed_orcids":["https://orcid.org/0000-0003-0049-3637"]},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Salam Khalifa","raw_affiliation_strings":["New York University Abu Dhabi","Stony Brook University Computational Approaches to Modeling Language (CAMeL) Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"Stony Brook University Computational Approaches to Modeling Language (CAMeL) Lab ,","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130344136","display_name":"Abed Qaddoumi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abed Qaddoumi","raw_affiliation_strings":["Institute for Advanced Computational Science , and Department of Linguistics","Stony Brook University Computational Approaches to Modeling Language (CAMeL) Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Advanced Computational Science , and Department of Linguistics","institution_ids":[]},{"raw_affiliation_string":"Stony Brook University Computational Approaches to Modeling Language (CAMeL) Lab ,","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Y. Habash","orcid":"https://orcid.org/0000-0002-1831-3457","observed_orcids":["https://orcid.org/0000-0002-1831-3457"]},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["New York University Abu Dhabi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021314411","display_name":"Owen Rambow","orcid":"https://orcid.org/0000-0003-2054-039X","observed_orcids":["https://orcid.org/0000-0003-2054-039X"]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Owen Rambow","raw_affiliation_strings":["Stony Brook University Computational Approaches to Modeling Language (CAMeL) Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University Computational Approaches to Modeling Language (CAMeL) Lab ,","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14529709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2296","last_page":"2307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9384999871253967,"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":0.9384999871253967,"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/T10730","display_name":"Language Development and Disorders","score":0.0333000011742115,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.008999999612569809,"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/egyptian-arabic","display_name":"Egyptian Arabic","score":0.9729999899864197},{"id":"https://openalex.org/keywords/child-directed-speech","display_name":"child-directed speech","score":0.8840000033378601},{"id":"https://openalex.org/keywords/childes-corpus","display_name":"CHILDES corpus","score":0.8840000033378601},{"id":"https://openalex.org/keywords/arabic-speech-recognition","display_name":"Arabic speech recognition","score":0.9190000295639038},{"id":"https://openalex.org/keywords/arabic-part-of-speech-tagging","display_name":"Arabic part-of-speech tagging","score":0.7139999866485596},{"id":"https://openalex.org/keywords/diacritization","display_name":"diacritization","score":0.7360000014305115},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.40400001406669617},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"language acquisition","score":0.5839999914169312},{"id":"https://openalex.org/keywords/speech-technology","display_name":"speech technology","score":0.3230000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5983999967575073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5809999704360962},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5076000094413757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625000059604645},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.241799995303154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.102","doi":"https://doi.org/10.18653/v1/2026.eacl-long.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.102","pdf_url":"https://aclanthology.org/2026.eacl-long.102.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.102","doi":"https://doi.org/10.18653/v1/2026.eacl-long.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.102","pdf_url":"https://aclanthology.org/2026.eacl-long.102.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331904","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140105413.pdf","grobid_xml":"https://content.openalex.org/works/W7140105413.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6960153712","https://openalex.org/W4415432665","https://openalex.org/W3208732477","https://openalex.org/W3029585093","https://openalex.org/W2970442528","https://openalex.org/W7134808479","https://openalex.org/W96807091","https://openalex.org/W4411630323","https://openalex.org/W2577201715","https://openalex.org/W131663347"],"abstract_inverted_index":{"We":[0],"present":[1],"ARABABYTALK-EGY,":[2],"an":[3],"enriched":[4],"release":[5],"of":[6,31,96],"the":[7,14,24,94],"Egyptian":[8,90],"Arabic":[9,20,43,57,79,91,105],"CHILDES":[10,26],"corpus,":[11],"that":[12],"opens":[13],"child-adult":[15],"interactions":[16],"genre":[17],"to":[18,40],"modern":[19],"NLP":[21,70],"research.Starting":[22],"from":[23],"original":[25],"recordings":[27],"and":[28,45,51,78,83,88,104],"IPA":[29,38],"transcriptions":[30],"caregiver-child":[32],"sessions,":[33],"we":[34],"(i)":[35],"map":[36],"each":[37],"token":[39],"fully":[41],"diacritized":[42],"script,":[44],"(ii)":[46],"add":[47],"core":[48],"part-of-speech":[49],"tags":[50],"lemmas":[52],"aligned":[53],"with":[54],"existing":[55],"dialectal":[56],"morphological":[58,76],"resources.These":[59],"layers":[60],"yield":[61],"\u223c26K":[62],"annotated":[63],"tokens":[64],"suitable":[65],"for":[66,100],"both":[67],"text-and":[68],"speech-based":[69],"tasks.We":[71],"provide":[72],"a":[73],"benchmark":[74],"on":[75],"disambiguation":[77],"ASR.We":[80],"outline":[81],"lexical":[82],"morphosyntactic":[84],"differences":[85],"between":[86],"ARABABYTALK-EGY":[87],"general":[89],"resources,":[92],"highlighting":[93],"value":[95],"genrespecific":[97],"training":[98],"data":[99],"language":[101],"acquisition":[102],"studies":[103],"speech":[106],"technology.":[107],"1":[108],"BP\u00e6bu-be":[109],"d\u00e6?":[110],"\u202b\u064e\ufee9\u061f\u202c":[111],"\u0650":[112],"\u202b\ufe8d\u202c":[113],"\u064f":[114],"\u202b\ufe83\u202c":[115]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}
