{"id":6465,"date":"2021-11-30T13:36:21","date_gmt":"2021-11-30T13:36:21","guid":{"rendered":"https:\/\/sadilar.org\/enabling-localised-language-technology-applications\/"},"modified":"2021-11-30T13:36:21","modified_gmt":"2021-11-30T13:36:21","slug":"enabling-localised-language-technology-applications","status":"publish","type":"post","link":"https:\/\/sadilar.org\/en\/enabling-localised-language-technology-applications\/","title":{"rendered":"Enabling localised language technology applications: A Computational Wide coverage resource grammar for isiZulu"},"content":{"rendered":"<div class=\"googlefontscall\"><\/div>\n<div class=\"pagebuilderckparams\" data-colorpalettefromtemplate=\"\" data-colorpalettefromsettings=\",,,,\" data-styles=\"\"><\/div>\n<div class=\"rowck ckstack3 ckstack2 ckstack1 uick-sortable\" id=\"row_ID1638279331714\" data-gutter=\"2%\" data-nb=\"1\" style=\"position: relative;\">\n<style class=\"ckcolumnwidth\">[data-gutter=\"2%\"][data-nb=\"1\"]:not(.ckadvancedlayout) [data-width=\"100\"] {width:100%;}[data-gutter=\"2%\"][data-nb=\"1\"].ckadvancedlayout [data-width=\"100\"] {width:100%;}<\/style>\n<div class=\"inner animate clearfix\">\n<div class=\"blockck\" id=\"block_ID1638279331714\" data-real-width=\"100%\" data-width=\"100\" style=\"position: relative;\">\n<div class=\"ckstyle\"><\/div>\n<div class=\"inner animate resizable\">\n<div class=\"innercontent uick-sortable\">\n<div id=\"ID1638279331735\" class=\"cktype\" data-type=\"text\" style=\"position: relative;\">\n<div class=\"tab_effects ckprops\" fieldslist=\"\"><\/div>\n<div class=\"tab_blocstyles ckprops\" blocbackgroundpositionend=\"100\" blocbackgrounddirection=\"topbottom\" blocbackgroundimageattachment=\"scroll\" blocbackgroundimagerepeat=\"no-repeat\" blocbackgroundimagesize=\"auto\" blocbordertopstyle=\"solid\" blocborderrightstyle=\"solid\" blocborderbottomstyle=\"solid\" blocborderleftstyle=\"solid\" blocbordersstyle=\"solid\" blocshadowinset=\"0\" fieldslist=\"blocbackgroundpositionend,blocbackgrounddirection,blocbackgroundimageattachment,blocbackgroundimagerepeat,blocbackgroundimagesize,blocalignementleft,blocalignementcenter,blocalignementright,blocalignementjustify,blocbordertopstyle,blocborderrightstyle,blocborderbottomstyle,blocborderleftstyle,blocbordersstyle,blocshadowinset\"><\/div>\n<div class=\"tab_edition ckprops\" fieldslist=\"\"><\/div>\n<div class=\"ckstyle\">\n<style><\/style>\n<\/div>\n<div class=\"cktext inner\" style=\"position: relative;\" spellcheck=\"false\">\n<p><strong>Project Type: <\/strong>Node<br \/><strong>Project Start Date: <\/strong>1 April 2020<br \/><strong>Project Status: <\/strong>Completed&nbsp;<\/p>\n<p><strong>Project Aims:<\/strong><\/p>\n<p>The CSIR node of SADiLaR recently completed a project with as its main aim to deliver to the research community a high-quality, computational, wide coverage resource grammar (WCRG) for isiZulu.&nbsp; WCRGs unlock opportunities for the South African languages to participate in multilingual research, nationally and internationally.<\/p>\n<p>The project focused on developing various foundational components of the WCRG, namely the isiZulu resource grammar itself, a lexicon aimed at enabling wide-coverage, and a framework for development and evaluation based on a manually curated treebank. Furthermore, an extension module was developed to enable chunk parsing via the grammar, and a web service was developed to provide parsing and linearisation functionality. A web user interface was developed to showcase the isiZulu RG and make it available to the Natural Language Processing (NLP) community as end users.<\/p>\n<p>&nbsp;<strong>Project Deliverables: <\/strong><\/p>\n<p><em>1. Resource Grammar for isiZulu<\/em><\/p>\n<p>Implementation of isiZulu RG functions, merged into the official GF RGL repository<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/GrammaticalFramework\/gf-rgl\" data-mce-href=\"https:\/\/github.com\/GrammaticalFramework\/gf-rgl\">https:\/\/github.com\/GrammaticalFramework\/gf-rgl<\/a><\/p>\n<p><em>2. GF Lexicon modules<\/em><\/p>\n<p>Monolingual and multilingual GF concrete and abstract syntax modules<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/GrammaticalFramework\/gf-rgl\" data-mce-href=\"https:\/\/github.com\/GrammaticalFramework\/gf-rgl\">https:\/\/github.com\/GrammaticalFramework\/gf-rgl<\/a><\/p>\n<p>Phrase-level adjectival qualificative GF concrete and abstract syntax modules<\/p>\n<p>Access at:&nbsp;<a href=\"https:\/\/github.com\/LauretteM\/gf-afwn\" data-mce-href=\"https:\/\/github.com\/LauretteM\/gf-afwn\">https:\/\/github.com\/LauretteM\/gf-afwn<\/a><\/p>\n<p><em>3. Treebanks<\/em><\/p>\n<p>A manually curated treebank of 1000 sentences was developed and a&nbsp;set of treebanks for regression testing was developed<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\" data-mce-href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\">https:\/\/github.com\/LauretteM\/gf-zulu-resources<\/a><\/p>\n<p>Automatically generated treebanks: VulaBula Graded Reader treebank, isiZulu Wordnet usage examples treebank<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\" data-mce-href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\">https:\/\/github.com\/LauretteM\/gf-zulu-resources<\/a><\/p>\n<p><em>4. GF chunk extension module<\/em><\/p>\n<p>GF modules PChunk.gf and PChunkZul.gf, merged into the official GF RGL repository<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/GrammaticalFramework\/gf-rgl\" data-mce-href=\"https:\/\/github.com\/GrammaticalFramework\/gf-rgl\">https:\/\/github.com\/GrammaticalFramework\/gf-rgl<\/a><\/p>\n<p><em>5. REST API web service and a web user interface<\/em><\/p>\n<p>A web service for parsing of isiZulu sentences and linearisation of abstract parse trees.<\/p>\n<p>Access at: <a href=\"https:\/\/rhonda.qfrency.com\/api\/v1\/mt\/zulurg\/v1\" data-mce-href=\"https:\/\/rhonda.qfrency.com\/api\/v1\/mt\/zulurg\/v1\">https:\/\/rhonda.qfrency.com\/api\/v1\/mt\/zulurg\/v1<\/a><\/p>\n<p>A web user interface to serve end users of the RG.<\/p>\n<p>Access at: <a href=\"https:\/\/grammar.qfrency.com\/\" data-mce-href=\"https:\/\/grammar.qfrency.com\/\">https:\/\/grammar.qfrency.com\/<\/a><\/p>\n<p><em>6. Capacity development and research outputs<\/em><\/p>\n<p>Slides presented at GF Summer School<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\" data-mce-href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\">https:\/\/github.com\/LauretteM\/gf-zulu-resources<\/a><\/p>\n<p>Slides presented at GF online seminars<\/p>\n<p>Access at: <a href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\" data-mce-href=\"https:\/\/github.com\/LauretteM\/gf-zulu-resources\">https:\/\/github.com\/LauretteM\/gf-zulu-resources<\/a>&nbsp;&nbsp;<\/p>\n<p>International workshop<\/p>\n<p>Listed here: <a href=\"https:\/\/www.eventbrite.co.uk\/e\/language-technology-for-education-in-the-south-african-languages-registration-349430665527\" data-mce-href=\"https:\/\/www.eventbrite.co.uk\/e\/language-technology-for-education-in-the-south-african-languages-registration-349430665527\">https:\/\/www.eventbrite.co.uk\/e\/language-technology-for-education-in-the-south-african-languages-registration-349430665527<\/a><\/p>\n<p>Title: Approximating a Zulu GF concrete syntax with a neural network for natural language understanding<\/p>\n<p>Presented at CNL 2021<\/p>\n<p>Access at: <a href=\"https:\/\/sadilar.org\/wp-content\/uploads\/2021\/11\/2021.cnl-1.4.pdf\" data-mce-href=\"https:\/\/sadilar.org\/wp-content\/uploads\/2021\/11\/2021.cnl-1.4.pdf\">https:\/\/sadilar.org\/wp-content\/uploads\/2021\/11\/2021.cnl-1.4.pdf<\/a><\/p>\n<p>Title: Extending the Usage of Adjectives in the Zulu AfWN<\/p>\n<p>Presented at GWC 2023<\/p>\n<p>Access at: <a href=\"https:\/\/sadilar.org\/wp-content\/uploads\/2021\/11\/GWC2023_paper_5400.pdf\" data-mce-href=\"https:\/\/sadilar.org\/wp-content\/uploads\/2021\/11\/GWC2023_paper_5400.pdf\">https:\/\/sadilar.org\/wp-content\/uploads\/2021\/11\/GWC2023_paper_5400.pdf<\/a><\/p>\n<p>Title: Parsing Zulu text using Grammatical Framework<\/p>\n<p>Submitted to CLIRAI (special session) 2023<\/p>\n<p>Not available yet.<\/p>\n<p>Title: Leveraging a resource grammar for developing language resources for Zulu<\/p>\n<p>Submitted to Language, Resources and Evaluation<\/p>\n<p>Not available yet<\/p>\n<p>&nbsp;<\/p>\n<p><strong>Contact Person:<\/strong><\/p>\n<p>Dr Laurette Marais, node manager: <a href=\"mailto:LMarais@csir.co.za\" data-mce-href=\"mailto:LMarais@csir.co.za\">LMarais@csir.co.za<\/a>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"ckstyle\"><\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Project Type: NodeProject Start Date: 1 April 2020Project Status: Completed&nbsp; Project Aims: The CSIR node of SADiLaR recently completed a project with as its main aim to deliver to the research community a high-quality, computational, wide coverage resource grammar (WCRG) for isiZulu.&nbsp; WCRGs unlock opportunities for the South African languages to participate in multilingual research, [&hellip;]<\/p>\n","protected":false},"author":246,"featured_media":0,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[730],"tags":[],"class_list":["post-6465","post","type-post","status-publish","format-standard","hentry","category-general"],"acf":[],"_links":{"self":[{"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/posts\/6465","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/users\/246"}],"replies":[{"embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/comments?post=6465"}],"version-history":[{"count":0,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/posts\/6465\/revisions"}],"wp:attachment":[{"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/media?parent=6465"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/categories?post=6465"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/tags?post=6465"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}