{"id":"https://openalex.org/W4416035672","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1284","title":"Morpheme Induction for Emergent Language","display_name":"Morpheme Induction for Emergent Language","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035672","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1284"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1284","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1284","pdf_url":"https://aclanthology.org/2025.emnlp-main.1284.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1284.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058548942","display_name":"Brendon Boldt","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brendon Boldt","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh , PA , USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh , PA , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University Pittsburgh , PA , USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University Pittsburgh , PA , USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058548942"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3889567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25275","last_page":"25290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.38119998574256897,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.38119998574256897,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11445","display_name":"Origins and Evolution of Life","score":0.10159999877214432,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.07980000227689743,"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/morpheme","display_name":"Morpheme","score":0.9420999884605408},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47450000047683716},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3305000066757202},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2976999878883362},{"id":"https://openalex.org/keywords/human-language","display_name":"Human language","score":0.251800000667572}],"concepts":[{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.9420999884605408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678600013256073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6453999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122000217437744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1284","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1284","pdf_url":"https://aclanthology.org/2025.emnlp-main.1284.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1284","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1284","pdf_url":"https://aclanthology.org/2025.emnlp-main.1284.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035672.pdf","grobid_xml":"https://content.openalex.org/works/W4416035672.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"CSAR,":[2],"an":[3],"algorithm":[4,20,87],"for":[5,72],"inducing":[6],"morphemes":[7,24,52],"from":[8,41],"emergent":[9,99],"language":[10,81],"corpora":[11],"of":[12,59,98,106],"parallel":[13],"utterances":[14],"and":[15,31,44,68,108],"meanings.It":[16],"is":[17,61],"a":[18,96],"greedy":[19],"that":[21,85],"(1)":[22],"weights":[23],"based":[25],"on":[26,64,79],"mutual":[27],"information":[28],"between":[29],"forms":[30],"meanings,":[32],"(2)":[33],"selects":[34],"the":[35,42,47,86],"highest-weighted":[36],"pair,":[37],"(3)":[38],"removes":[39],"it":[40],"corpus,":[43],"(4)":[45],"repeats":[46],"process":[48],"to":[49,83],"induce":[50],"further":[51],"(i.e.,":[53],"Count,":[54],"Select,":[55],"Ablate,":[56],"Repeat).The":[57],"effectiveness":[58],"CSAR":[60],"first":[62],"validated":[63],"procedurally":[65],"generated":[66],"datasets":[67],"compared":[69],"against":[70],"baselines":[71],"related":[73],"tasks.Second,":[74],"we":[75,94],"validate":[76],"CSAR's":[77],"performance":[78],"human":[80],"data":[82],"show":[84],"makes":[88],"reasonable":[89],"predictions":[90],"in":[91],"adjacent":[92],"domains.Finally,":[93],"analyze":[95],"handful":[97],"languages,":[100],"quantifying":[101],"linguistic":[102],"characteristics":[103],"like":[104],"degree":[105],"synonymy":[107],"polysemy.":[109]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-11-08T00:00:00"}