{"id":"https://openalex.org/W4416033917","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1218","title":"Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models","display_name":"Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033917","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1218"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1218","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1218.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1218.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114353445","display_name":"Mahta Fetrat Qharabagh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahta Fetrat Qharabagh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114353446","display_name":"Zahra Dehghanian","orcid":null},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Zahra Dehghanian","raw_affiliation_strings":["Dept. of Computer Engineering Sharif University of Technology / Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Engineering Sharif University of Technology / Tehran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063512925","display_name":"Hamid R. Rabiee","orcid":"https://orcid.org/0000-0002-9835-4493"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hamid R. Rabiee","raw_affiliation_strings":["Dept. of Computer Engineering Sharif University of Technology / Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Engineering Sharif University of Technology / Tehran","institution_ids":["https://openalex.org/I133529467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6485,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85607913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"22382","last_page":"22408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.2935999929904938,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.2935999929904938,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.05950000137090683,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.05169999971985817,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/statistical-model","display_name":"Statistical model","score":0.5672000050544739},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.35740000009536743},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2703000009059906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26930001378059387},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.26809999346733093},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.2669000029563904}],"concepts":[{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5672000050544739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4690000116825104},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35690000653266907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1218","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1218.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1218","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1218","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1218.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033917.pdf","grobid_xml":"https://content.openalex.org/works/W4416033917.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Homograph":[0],"disambiguation":[1,31,144],"remains":[2],"a":[3,58,82,93,129],"significant":[4],"challenge":[5,14],"in":[6,142],"grapheme-to-phoneme":[7],"(G2P)":[8],"conversion,":[9],"especially":[10],"for":[11,39,61,88,92,108,146],"low-resource":[12],"languages.This":[13],"is":[15,24],"twofold:":[16],"(1)":[17],"creating":[18],"balanced":[19],"and":[20,26,28,46,73,150],"comprehensive":[21],"homograph":[22,143],"datasets":[23,98],"labor-intensive":[25],"costly,":[27],"(2)":[29],"specific":[30],"strategies":[32],"introduce":[33,65],"additional":[34],"latency,":[35],"making":[36],"them":[37],"unsuitable":[38],"real-time":[40],"applications":[41,111],"such":[42],"as":[43],"screen":[44,113],"readers":[45],"other":[47],"accessibility":[48,110],"tools.In":[49],"this":[50,71,115],"paper,":[51],"we":[52,56,90,117],"address":[53],"both":[54],"issues.First,":[55],"propose":[57],"semi-automated":[59],"pipeline":[60],"constructing":[62],"homograph-focused":[63],"datasets,":[64],"the":[66,101,121,147],"Ho-moRich":[67],"dataset":[68],"generated":[69],"through":[70],"pipeline,":[72],"demonstrate":[74],"its":[75],"effectiveness":[76],"by":[77],"applying":[78],"it":[79],"to":[80,99],"enhance":[81],"state-of-the-art":[83],"deep":[84,148],"learningbased":[85],"G2P":[86,125],"system":[87],"Persian.Second,":[89],"advocate":[91],"paradigm":[94],"shift-utilizing":[95],"rich":[96],"offline":[97],"inform":[100],"development":[102],"of":[103,120],"fast,":[104],"statistical":[105],"methods":[106],"suitable":[107],"latencysensitive":[109],"like":[112],"readers.To":[114],"end,":[116],"improve":[118],"one":[119],"most":[122],"well-known":[123],"rule-based":[124],"systems,":[126],"eSpeak,":[127],"into":[128],"fast":[130],"homograph-aware":[131],"version,":[132],"Ho-moFast":[133],"eSpeak.Our":[134],"results":[135],"show":[136],"an":[137],"approximate":[138],"30":[139],"percentage-point":[140],"improvement":[141],"accuracy":[145],"learning-based":[149],"eSpeak":[151],"systems.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-08T00:00:00"}