{"id":"https://openalex.org/W4416035639","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1310","title":"Less is More: The Effectiveness of Compact Typological Language Representations","display_name":"Less is More: The Effectiveness of Compact Typological Language Representations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035639","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1310"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1310","pdf_url":"https://aclanthology.org/2025.emnlp-main.1310.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.1310.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120265941","display_name":"York Hay Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"York Hay Ng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102745583","display_name":"Phuong H. Hoang","orcid":"https://orcid.org/0000-0002-2150-9231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phuong Hanh Hoang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013354989","display_name":"En-Shiun Annie Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"En-Shiun Annie Lee","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120265941"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38997225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25816","last_page":"25827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.18150000274181366,"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":0.18150000274181366,"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/T10730","display_name":"Language Development and Disorders","score":0.12250000238418579,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.09319999814033508,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32690000534057617},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2962000072002411},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2935999929904938},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2870999872684479},{"id":"https://openalex.org/keywords/proposition","display_name":"Proposition","score":0.28119999170303345},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25859999656677246}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.531000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5060999989509583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2777152325","wikidata":"https://www.wikidata.org/wiki/Q108163","display_name":"Proposition","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1310","pdf_url":"https://aclanthology.org/2025.emnlp-main.1310.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.1310","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1310","pdf_url":"https://aclanthology.org/2025.emnlp-main.1310.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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035639.pdf","grobid_xml":"https://content.openalex.org/works/W4416035639.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Linguistic":[0],"feature":[1,36,40,52],"datasets":[2],"such":[3],"as":[4],"URIEL+":[5,34],"are":[6],"valuable":[7],"for":[8,19],"modelling":[9],"cross-lingual":[10],"relationships,":[11],"but":[12],"their":[13],"high":[14],"dimensionality":[15],"and":[16,42,58,74],"sparsity,":[17],"especially":[18],"low-resource":[20],"languages,":[21],"limit":[22],"the":[23,33],"effectiveness":[24],"of":[25,65],"distance":[26,56,72],"metrics.We":[27],"propose":[28],"a":[29],"pipeline":[30],"to":[31],"optimize":[32],"typological":[35,48],"space":[37],"by":[38],"combining":[39],"selection":[41],"imputation,":[43],"producing":[44],"compact":[45],"yet":[46],"interpretable":[47],"representations.We":[49],"evaluate":[50],"these":[51],"subsets":[53],"on":[54],"linguistic":[55],"alignment":[57],"downstream":[59],"tasks,":[60],"demonstrating":[61],"that":[62],"reduced-size":[63],"representations":[64],"language":[66],"typology":[67],"can":[68],"yield":[69],"more":[70],"informative":[71],"metrics":[73],"improve":[75],"performance":[76],"in":[77],"multilingual":[78],"NLP":[79],"applications.":[80]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}