{"id":"https://openalex.org/W7166851726","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1632","title":"Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights","display_name":"Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166851726","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1632"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1632","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1632","pdf_url":"https://aclanthology.org/2026.findings-acl.1632.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1632.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016534605","display_name":"Maharaj Brahma","orcid":"https://orcid.org/0000-0002-0155-3745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maharaj Brahma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139791930","display_name":"N J Karthika","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N J Karthika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129651085","display_name":"Rajat Verma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajat Verma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120715405","display_name":"Nagasai Saketh Naidu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nagasai Saketh Naidu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139720820","display_name":"Rohit Saluja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Saluja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087152480","display_name":"Maunendra Sankar Desarkar","orcid":"https://orcid.org/0000-0003-1963-7338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maunendra Sankar Desarkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139805094","display_name":"Ganesh Ramakrishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganesh Ramakrishnan","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84110012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32614","last_page":"32632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.44699999690055847,"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":0.44699999690055847,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.019999999552965164,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T12090","display_name":"Language and cultural evolution","score":0.016499999910593033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.42980000376701355},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3449999988079071},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.34459999203681946},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.30320000648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24869999289512634},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.24740000069141388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1632","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1632","pdf_url":"https://aclanthology.org/2026.findings-acl.1632.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1632","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1632","pdf_url":"https://aclanthology.org/2026.findings-acl.1632.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8235525488853455,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323448","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152"},{"id":"https://openalex.org/F4320326797","display_name":"Indian Institute of Technology Mandi","ror":"https://ror.org/05r9r2f34"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166851726.pdf","grobid_xml":"https://content.openalex.org/works/W7166851726.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Maharaj":[0],"Brahma,":[1],"N":[2],"J":[3],"Karthika,":[4],"Rajat":[5],"Verma,":[6],"Nagasai":[7],"Saketh":[8],"Naidu,":[9],"Rohit":[10],"Saluja,":[11],"Maunendra":[12],"Sankar":[13],"Desarkar,":[14],"Ganesh":[15],"Ramakrishnan.":[16],"Findings":[17],"of":[18],"the":[19],"Association":[20],"for":[21],"Computational":[22],"Linguistics:":[23],"ACL":[24],"2026.":[25,26]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
