{"id":"https://openalex.org/W3038489922","doi":"https://doi.org/10.1145/3390298","title":"Morphological Segmentation to Improve Crosslingual Word Embeddings for Low Resource Languages","display_name":"Morphological Segmentation to Improve Crosslingual Word Embeddings for Low Resource Languages","publication_year":2020,"publication_date":"2020-06-21","ids":{"openalex":"https://openalex.org/W3038489922","doi":"https://doi.org/10.1145/3390298","mag":"3038489922"},"language":"en","primary_location":{"id":"doi:10.1145/3390298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3390298","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014235946","display_name":"Santwana Chimalamarri","orcid":"https://orcid.org/0000-0003-1343-8792"},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Santwana Chimalamarri","raw_affiliation_strings":["PES University, Bangalore, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"PES University, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008942513","display_name":"Dinkar Sitaram","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dinkar Sitaram","raw_affiliation_strings":["PES University, Bangalore, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"PES University, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004678878","display_name":"Ashritha Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashritha Jain","raw_affiliation_strings":["PES University, Bangalore, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"PES University, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I196608512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014235946"],"corresponding_institution_ids":["https://openalex.org/I196608512"],"apc_list":null,"apc_paid":null,"fwci":1.2347,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84058151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"5","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9912999868392944,"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/agglutinative-language","display_name":"Agglutinative language","score":0.8864795565605164},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":0.8265094757080078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7788244485855103},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.7323593497276306},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6987124681472778},{"id":"https://openalex.org/keywords/language-family","display_name":"Language family","score":0.6369110345840454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6364307403564453},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5226418972015381},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4460964500904083},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37231194972991943}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.8864795565605164},{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.8265094757080078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788244485855103},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.7323593497276306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6987124681472778},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.6369110345840454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6364307403564453},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5226418972015381},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4460964500904083},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37231194972991943},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3390298","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3390298","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1498990157","https://openalex.org/W1524281572","https://openalex.org/W2095333428","https://openalex.org/W2126725946","https://openalex.org/W2133564696","https://openalex.org/W2241862190","https://openalex.org/W2489487449","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2560674852","https://openalex.org/W2610850660","https://openalex.org/W2612560781","https://openalex.org/W2914304175","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2962795068","https://openalex.org/W2963174553","https://openalex.org/W2963206679","https://openalex.org/W2963993537","https://openalex.org/W2997617958","https://openalex.org/W2998704965","https://openalex.org/W3098341425","https://openalex.org/W3183153947","https://openalex.org/W4389521028"],"related_works":["https://openalex.org/W607176272","https://openalex.org/W2569651698","https://openalex.org/W2110699760","https://openalex.org/W3134916539","https://openalex.org/W4309803833","https://openalex.org/W3135204554","https://openalex.org/W4382561672","https://openalex.org/W2810296466","https://openalex.org/W2950091200","https://openalex.org/W2963939565"],"abstract_inverted_index":{"Crosslingual":[0],"word":[1,82],"embeddings":[2,36,83],"developed":[3],"from":[4],"multiple":[5],"parallel":[6],"corpora":[7,75],"help":[8],"in":[9,24],"understanding":[10],"the":[11,17,41,74,78,91,113,133],"relationships":[12],"between":[13],"languages":[14,27,55],"and":[15,30,47,87,94,110,137],"improving":[16],"prediction":[18,92],"quality":[19,93],"of":[20,43,80,112],"machine":[21],"translation.":[22],"However,":[23],"low":[25],"resource":[26],"with":[28],"complex":[29,44],"agglutinative":[31],"morphologies,":[32],"inducing":[33],"good-quality":[34],"crosslingual":[35,81],"becomes":[37],"challenging":[38],"due":[39],"to":[40,77,132],"problem":[42],"morphological":[45,71],"forms":[46],"rare":[48],"words.":[49],"This":[50],"is":[51],"true":[52],"even":[53],"for":[54,84],"that":[56,67],"share":[57],"common":[58],"linguistic":[59],"structure.":[60],"In":[61],"our":[62,121],"work,":[63],"we":[64,103],"have":[65,104,118,138],"shown":[66],"performing":[68],"a":[69,124],"simple":[70],"segmentation":[72],"upon":[73,123],"prior":[76],"generation":[79],"both":[85],"roots":[86],"suffixes":[88],"greatly":[89],"improves":[90],"captures":[95],"semantic":[96],"similarities":[97],"more":[98],"effectively.":[99],"To":[100],"exhibit":[101],"this,":[102],"chosen":[105],"two":[106],"related":[107],"languages:":[108],"Telugu":[109],"Kannada":[111],"Dravidian":[114],"language":[115,135],"family.":[116],"We":[117],"also":[119],"tested":[120],"method":[122],"widely":[125],"spoken":[126],"North":[127],"Indian":[128],"language,":[129],"Hindi,":[130],"belonging":[131],"Indo-European":[134],"family,":[136],"observed":[139],"encouraging":[140],"results.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}