{"id":"https://openalex.org/W7130722367","doi":"https://doi.org/10.17863/cam.125909","title":"From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes","display_name":"From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W7130722367","doi":"https://doi.org/10.17863/cam.125909"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.22906","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.22906","pdf_url":"https://arxiv.org/pdf/2410.22906","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/2410.22906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092850350","display_name":"Z\u00e9bulon Goriely","orcid":"https://orcid.org/0000-0002-8877-4099","observed_orcids":["https://orcid.org/0000-0002-8877-4099"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goriely, Z","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126312955","display_name":"RD Martinez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martinez, RD","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069029343","display_name":"Andrew Caines","orcid":"https://orcid.org/0000-0001-9647-4902","observed_orcids":["https://orcid.org/0000-0001-9647-4902"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caines, A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087195265","display_name":"Lisa Beinborn","orcid":"https://orcid.org/0000-0001-8654-2190","observed_orcids":["https://orcid.org/0000-0001-8654-2190"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beinborn, L","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138675282","display_name":"Paula Buttery","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buttery, P","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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.5249000191688538,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.5249000191688538,"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":0.2734000086784363,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1527000069618225,"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/babylm","display_name":"BabyLM","score":0.671999990940094},{"id":"https://openalex.org/keywords/language-model-pretraining","display_name":"language model pretraining","score":0.6790000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324999809265137},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7457000017166138},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6202999949455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644999742507935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4221000075340271},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.2994999885559082},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C151670969","wikidata":"https://www.wikidata.org/wiki/Q7187303","display_name":"Phonological rule","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2410.22906","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.22906","pdf_url":"https://arxiv.org/pdf/2410.22906","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":"pmh:oai:www.repository.cam.ac.uk:1810/396616","doi":null,"is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/396616","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Conference Object"},{"id":"doi:10.48550/arxiv.2410.22906","doi":"https://doi.org/10.48550/arxiv.2410.22906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.22906","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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17863/cam.125909","doi":"https://doi.org/10.17863/cam.125909","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.125909","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.22906","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.22906","pdf_url":"https://arxiv.org/pdf/2410.22906","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1690597291","display_name":null,"funder_award_id":"#OPP1144","funder_id":"https://openalex.org/F4320323264","funder_display_name":"Gates Cambridge Trust"},{"id":"https://openalex.org/G2264885075","display_name":null,"funder_award_id":"OPP1144","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5477836236","display_name":"Cambridge University Development Office in the United States Inc (CUDOUS) - to endow a global scholarship program at the post-baccalaureate level for academically gifted students","funder_award_id":"OPP1144","funder_id":"https://openalex.org/F4320306137","funder_display_name":"Bill and Melinda Gates Foundation"},{"id":"https://openalex.org/G581313191","display_name":null,"funder_award_id":"EP/T022159/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7002347110","display_name":"Cambridge Service for Data Driven Discovery (CSD3) - A National Data Intensive Science Cloud for Converged Simulation, AI & Analytics","funder_award_id":"EP/T022159/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7028966183","display_name":null,"funder_award_id":"EP/T022159/1","funder_id":"https://openalex.org/F4320334632","funder_display_name":"Science and Technology Facilities Council"}],"funders":[{"id":"https://openalex.org/F4320306137","display_name":"Bill and Melinda Gates Foundation","ror":"https://ror.org/0456r8d26"},{"id":"https://openalex.org/F4320312927","display_name":"Dell EMC","ror":"https://ror.org/05rejmm18"},{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"},{"id":"https://openalex.org/F4320323264","display_name":"Gates Cambridge Trust","ror":"https://ror.org/033sn5p83"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7130722367.pdf","grobid_xml":"https://content.openalex.org/works/W7130722367.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128357279","https://openalex.org/W4404783544","https://openalex.org/W7165361711","https://openalex.org/W4412889068","https://openalex.org/W4415065457","https://openalex.org/W3129124668","https://openalex.org/W7165409758","https://openalex.org/W4402670210","https://openalex.org/W7071025486","https://openalex.org/W7167512672"],"abstract_inverted_index":{"Language":[0],"models":[1],"are":[2,58],"typically":[3],"trained":[4],"on":[5,42,122],"large":[6],"corpora":[7],"of":[8,26,52,76],"text":[9,70],"in":[10,48],"their":[11],"default":[12],"orthographic":[13],"form.":[14],"However,":[15],"this":[16,80],"is":[17],"not":[18],"the":[19,50,83,88],"only":[20],"option;":[21],"representing":[22],"data":[23],"as":[24,55,91,93],"streams":[25],"phonemes":[27],"can":[28],"offer":[29],"unique":[30],"advantages,":[31],"from":[32,87],"deeper":[33],"insights":[34],"into":[35,72],"phonological":[36],"language":[37,96,124],"acquisition":[38],"to":[39,68,82,94,102],"improved":[40],"performance":[41,121],"sound-based":[43],"tasks.":[44],"The":[45],"challenge":[46],"lies":[47],"evaluating":[49],"impact":[51],"phoneme-based":[53,117],"training,":[54],"most":[56],"benchmarks":[57],"also":[59],"orthographic.":[60],"To":[61],"address":[62],"this,":[63],"we":[64],"develop":[65],"a":[66,73,106],"pipeline":[67,81],"convert":[69],"datasets":[71],"continuous":[74],"stream":[75],"phonemes.":[77],"We":[78],"apply":[79],"100-million-word":[84],"pre-training":[85],"dataset":[86],"BabyLM":[89],"challenge,":[90],"well":[92],"standard":[95],"and":[97,104,131],"grammatical":[98],"benchmarks,":[99],"enabling":[100],"us":[101],"pre-train":[103],"evaluate":[105],"model":[107],"using":[108],"phonemic":[109],"input":[110],"representations.":[111],"Our":[112],"results":[113],"show":[114],"that":[115],"while":[116],"training":[118],"slightly":[119],"reduces":[120],"traditional":[123],"understanding":[125],"tasks,":[126],"it":[127],"offers":[128],"valuable":[129],"analytical":[130],"practical":[132],"benefits.":[133]},"counts_by_year":[],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2026-02-21T00:00:00"}