{"id":"https://openalex.org/W7166825300","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1740","title":"Linear Semantic Segmentation for Low-Resource Spoken Dialects","display_name":"Linear Semantic Segmentation for Low-Resource Spoken Dialects","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166825300","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1740"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1740","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1740","pdf_url":"https://aclanthology.org/2026.findings-acl.1740.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1740.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117865139","display_name":"Kirill Chirkunov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kirill Chirkunov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086381528","display_name":"Younes Samih","orcid":"https://orcid.org/0000-0002-0485-7920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Younes Samih","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087143068","display_name":"Abed Alhakim Freihat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abed Alhakim Freihat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002602581","display_name":"Hanan Aldarmaki","orcid":"https://orcid.org/0000-0003-1706-1777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanan Aldarmaki","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81490052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34844","last_page":"34861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4690000116825104,"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":0.4690000116825104,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.21150000393390656,"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/T12031","display_name":"Speech and dialogue systems","score":0.042100001126527786,"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/segmentation","display_name":"Segmentation","score":0.5310999751091003},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30970001220703125},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.26750001311302185},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2451000064611435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6061000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457000136375427},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4505000114440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2451000064611435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.23899999260902405}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1740","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1740","pdf_url":"https://aclanthology.org/2026.findings-acl.1740.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1740","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1740","pdf_url":"https://aclanthology.org/2026.findings-acl.1740.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166825300.pdf","grobid_xml":"https://content.openalex.org/works/W7166825300.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,43,59,96,112],"is":[2],"a":[3,49,111],"core":[4],"component":[5],"of":[6],"discourse":[7,38,122],"analysis,":[8],"yet":[9],"existing":[10],"models":[11,97],"are":[12,143],"primarily":[13],"developed":[14],"and":[15,35,77,82,85,119,133,141],"evaluated":[16],"on":[17,24,64,100,105,128],"highresource":[18],"written":[19],"text,":[20],"limiting":[21],"their":[22],"effectiveness":[23],"low-resource":[25,138],"spoken":[26,139],"varieties.In":[27],"particular,":[28],"dialectal":[29,65,106,129],"Arabic":[30,89],"exhibits":[31],"informal":[32],"syntax,":[33],"code-switching,":[34],"weakly":[36],"marked":[37],"structure":[39],"that":[40,95,114],"challenge":[41],"standard":[42],"approaches.In":[44],"this":[45,91],"paper,":[46],"we":[47,93],"introduce":[48],"new":[50],"multi-genre":[51],"benchmark":[52,67,132],"(more":[53],"than":[54],"1000":[55],"samples)":[56],"for":[57],"semantic":[58,117],"in":[60],"conversational":[61],"Arabic,":[62],"focusing":[63],"discourse.The":[66],"covers":[68],"transcribed":[69,107],"casual":[70],"telephone":[71],"conversations,":[72],"code-switched":[73],"podcasts,":[74],"broadcast":[75],"news,":[76],"expressive":[78],"dialogue":[79],"from":[80],"novels,":[81],"was":[83],"annotated":[84],"validated":[86],"by":[87],"native":[88],"annotators.Using":[90],"benchmark,":[92],"show":[94],"performing":[98],"well":[99],"MSA":[101],"news":[102],"genres":[103],"degrade":[104],"speech.We":[108],"further":[109],"propose":[110],"model":[113,142],"targets":[115],"local":[116],"coherence":[118],"robustness":[120],"to":[121,136],"discontinuities,":[123],"consistently":[124],"outperforming":[125],"strong":[126],"baselines":[127],"non-news":[130],"genres.The":[131],"approach":[134],"generalize":[135],"other":[137],"languages.Benchmark":[140],"available":[144],"online.":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}