{"id":"https://openalex.org/W7166527647","doi":"https://doi.org/10.63317/35ihcv2cfbzq","title":"Word segmentation for UD: a comparison of isiZulu and Sepedi","display_name":"Word segmentation for UD: a comparison of isiZulu and Sepedi","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166527647","doi":"https://doi.org/10.63317/35ihcv2cfbzq"},"language":null,"primary_location":{"id":"doi:10.63317/35ihcv2cfbzq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/35ihcv2cfbzq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/udw/pdf/2026.udw-1.10.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/udw/pdf/2026.udw-1.10.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139587457","display_name":"Laurette Marais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurette Marais","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015337389","display_name":"Laurette Pretorius","orcid":"https://orcid.org/0000-0003-3341-4675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurette Pretorius","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":0.76066603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.33230000734329224,"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":0.33230000734329224,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.225600004196167,"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"}},{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.06390000134706497,"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/bantu-languages","display_name":"Bantu languages","score":0.8070999979972839},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.7368000149726868},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.7006000280380249},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.4278999865055084},{"id":"https://openalex.org/keywords/languages-of-africa","display_name":"Languages of Africa","score":0.361299991607666},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.3122999966144562},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3025999963283539}],"concepts":[{"id":"https://openalex.org/C99878080","wikidata":"https://www.wikidata.org/wiki/Q33146","display_name":"Bantu languages","level":2,"score":0.8070999979972839},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.7368000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703499972820282},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.7006000280380249},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026999950408936},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5357999801635742},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C108494575","wikidata":"https://www.wikidata.org/wiki/Q207930","display_name":"Languages of Africa","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C132165367","wikidata":"https://www.wikidata.org/wiki/Q34049","display_name":"Semitic languages","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2778428490","wikidata":"https://www.wikidata.org/wiki/Q62155","display_name":"Affix","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/35ihcv2cfbzq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/35ihcv2cfbzq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/udw/pdf/2026.udw-1.10.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/35ihcv2cfbzq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/35ihcv2cfbzq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/udw/pdf/2026.udw-1.10.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5294744968414307,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166527647.pdf","grobid_xml":"https://content.openalex.org/works/W7166527647.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Southern":[1],"Bantu":[2],"language":[3],"family":[4],"contains":[5],"languages":[6,14,29,61],"with":[7,15,30,62],"so-called":[8],"conjunctive":[9,16],"orthographies":[10],"and":[11,37,85,106],"disjunctive":[12,31],"orthographies.In":[13],"orthographies,":[17,32],"such":[18],"as":[19,42],"isiZulu,":[20],"orthographic":[21,44,97],"words":[22,98],"correspond":[23],"to":[24,54],"linguistic":[25],"words,":[26,58],"whereas":[27],"in":[28],"prefix":[33],"morphemes":[34],"of":[35,74,89,96],"verbs":[36],"other":[38],"predicates":[39],"are":[40],"written":[41],"disjunct,":[43],"words.When":[45],"developing":[46],"Universal":[47],"Dependencies":[48],"treebanks,":[49],"the":[50,72,75,87,94],"basic":[51],"principle":[52],"is":[53],"consider":[55],"syntactic":[56],"(linguistic)":[57],"but":[59],"for":[60,104],"agglutinating":[63],"morphology,":[64],"it":[65],"has":[66],"been":[67],"argued":[68],"that":[69],"this":[70,77,81],"reduces":[71],"informativeness":[73],"treebank.In":[76],"paper":[78],"we":[79],"investigate":[80],"claim":[82],"by":[83],"analysing":[84],"measuring":[86],"effects":[88],"annotating":[90],"universal":[91],"dependencies":[92],"on":[93,99],"basis":[95],"two":[100],"morphosyntactically":[101],"parallel":[102],"treebanks":[103],"isiZulu":[105],"Sepedi.":[107]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}
