{"id":"https://openalex.org/W7128370844","doi":"https://doi.org/10.48550/arxiv.2602.06307","title":"Lost in Speech: Benchmarking, Evaluation, and Parsing of Spoken Bilingual Conversational Language Beyond Standard UD Assumptions","display_name":"Lost in Speech: Benchmarking, Evaluation, and Parsing of Spoken Bilingual Conversational Language Beyond Standard UD Assumptions","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128370844","doi":"https://doi.org/10.48550/arxiv.2602.06307"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2602.06307","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.06307","pdf_url":"https://arxiv.org/pdf/2602.06307","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.06307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117862385","display_name":"Nemika Tyagi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyagi, Nemika","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028941004","display_name":"Olga Kellert","orcid":"https://orcid.org/0000-0001-8601-8305","observed_orcids":["https://orcid.org/0000-0001-8601-8305"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kellert, Olga","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008941217","display_name":"Holly Hendrix","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hendrix, Holly","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308547","display_name":"Nelvin Licona-Guevara","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Licona-Guevara, Nelvin","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125385328","display_name":"Justin Mackie","orcid":"https://orcid.org/0009-0008-5984-3383","observed_orcids":["https://orcid.org/0009-0008-5984-3383"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mackie, Justin","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125387285","display_name":"Phanos Kareen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kareen, Phanos","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125423256","display_name":"Megan Michelle Smith","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Smith, Megan Michelle","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125412383","display_name":"Tatiana Gallego Hernande","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hernande, Tatiana Gallego","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104223276","display_name":"Samhitha Harish","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish, Samhitha","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126310603","display_name":"Chitta Baral","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baral, Chitta","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9932000041007996,"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":0.9932000041007996,"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":0.005400000140070915,"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":0.0005000000237487257,"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/dependency-parsing","display_name":"dependency parsing","score":0.8880000114440918},{"id":"https://openalex.org/keywords/universal-dependencies","display_name":"Universal Dependencies","score":0.8859999775886536},{"id":"https://openalex.org/keywords/speech-disfluency","display_name":"disfluency","score":0.6209999918937683},{"id":"https://openalex.org/keywords/english-spanish","display_name":"English-Spanish","score":0.7799999713897705}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8306000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015000224113464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6905999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.46970000863075256},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C2986991398","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntactic structure","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C101454708","wikidata":"https://www.wikidata.org/wiki/Q17106019","display_name":"Standard Model (mathematical formulation)","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.06307","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.06307","pdf_url":"https://arxiv.org/pdf/2602.06307","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.06307","doi":"https://doi.org/10.48550/arxiv.2602.06307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.06307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.06307","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.06307","pdf_url":"https://arxiv.org/pdf/2602.06307","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6220956444740295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128370844.pdf","grobid_xml":"https://content.openalex.org/works/W7128370844.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spoken":[0],"bilingual":[1,47],"conversations":[2],"pose":[3],"substantial":[4],"challenges":[5],"for":[6,56],"syntactic":[7,99],"parsing":[8,20,91,106],"because":[9],"they":[10],"often":[11],"include":[12],"disfluencies":[13],"and":[14,27,103,113,126],"discourse-driven":[15],"structures":[16],"that":[17,75,93,117,141],"complicate":[18],"dependency":[19,105],"under":[21,146],"standard":[22,147],"Universal":[23],"Dependencies":[24],"(UD)":[25],"assumptions":[26],"evaluation":[28,66,73],"practices.":[29],"To":[30,60],"systematically":[31],"study":[32],"these":[33],"challenges,":[34],"in":[35,131],"this":[36],"work,":[37],"we":[38,68,85],"first":[39],"introduce":[40,86],"a":[41,88],"linguistically":[42,81],"grounded":[43],"taxonomy":[44],"of":[45,64],"conversational":[46,124],"phenomena,":[48],"together":[49],"with":[50],"SpokeBench,":[51],"an":[52,71],"expert-annotated":[53],"English-Spanish":[54],"benchmark":[55],"structurally":[57],"complex":[58,123],"speech.":[59],"address":[61],"the":[62],"limitations":[63],"existing":[65],"practices,":[67],"propose":[69],"Flex-UD,":[70],"ambiguity-aware":[72],"metric":[74],"distinguishes":[76],"catastrophic":[77],"structural":[78],"failures":[79],"from":[80,97],"acceptable":[82],"variations.":[83],"Finally,":[84],"DECAP,":[87],"decoupled":[89],"agentic":[90],"framework":[92],"separates":[94],"spoken-phenomena":[95],"handling":[96],"core":[98],"analysis,":[100],"enabling":[101],"robust":[102],"interpretable":[104],"without":[107],"retraining.":[108],"Experiments":[109],"across":[110],"both":[111],"proprietary":[112],"open-weight":[114],"LLMs":[115],"show":[116],"DECAP":[118],"substantially":[119],"improves":[120],"performance":[121],"on":[122],"phenomena":[125],"achieves":[127],"over":[128,134],"60%":[129],"improvements":[130],"UPOS-F1":[132],"Score":[133],"baselines,":[135],"while":[136],"Flex-UD":[137],"evaluations":[138],"reveal":[139],"gains":[140],"otherwise":[142],"remain":[143],"partially":[144],"hidden":[145],"attachment-based":[148],"metrics.":[149]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-02-10T00:00:00"}
