{"id":6737,"date":"2020-11-04T08:39:53","date_gmt":"2020-11-04T08:39:53","guid":{"rendered":"https:\/\/sadilar.org\/sesotho-sa-leboa-part-of-speech-tagger\/"},"modified":"2023-08-24T14:57:15","modified_gmt":"2023-08-24T14:57:15","slug":"sesotho-sa-leboa-part-of-speech-tagger","status":"publish","type":"post","link":"https:\/\/sadilar.org\/en\/sesotho-sa-leboa-part-of-speech-tagger\/","title":{"rendered":"Naa part-of-speech tagger ke eng?"},"content":{"rendered":"

Author: Dimakatso Mathe<\/a> (SADiLaR Sesotho sa Leboa Researcher)<\/strong><\/span><\/p>\n

Part-of-speech tagger<\/em>, yeo e tla\u00a0 bit\u0161wago sehlathahlophant\u0161u<\/strong> go tloga mo, ke sediri\u0161wa sa theknolot\u0161i seo se diri\u0161wago go fetleka mant\u0161u ao a ngwadilwego a polelo ye e it\u0161ego gomme sa laet\u0161a gore mant\u0161u ao a wela dihlopheng dife t\u0161a mant\u0161u ka go phara setlankana se se hlalo\u0161ago sehlopha sa lent\u0161u (tag). Se \u0161omi\u0161a lenaneo la ditlankana (tagset) leo le ithekgilego ka dihlopha t\u0161a mant\u0161u t\u0161eo di filwego t\u0161a polelo gore se kgone go hlatha mant\u0161u. Dihlopha t\u0161a mant\u0161u di na le khuet\u0161o ye kgolo bokgoning bja setlabelwa se gore se hlathe goba gona go laet\u0161a dihlopha t\u0161a mant\u0161u. Gore re kgone go kwe\u0161i\u0161a se gabotse, re tla swanela ke go hlalo\u0161a ganyane ka dihlopha t\u0161a mant\u0161u t\u0161a Sesotho sa Leboa.<\/span><\/p>\n

Paulos le Louwrens (1994) ba hlalo\u0161a dihlopha t\u0161e lesome, e lego maina, ma\u0161ala, madiri, malahlelwa, makopanyi, mathu\u0161amadiri, mabot\u0161i\u0161i, ma\u0161upi, leba, gammgo le maamanyi. Go feta fao, dihlopha t\u0161a mant\u0161u t\u0161e dingwe di ka arolwa gape go ya ka mehuta goba dikarolwana t\u0161e di hwet\u0161agalo ka fase ga lent\u0161ukakaret\u0161o la sehlopha sa mant\u0161u. Go fa mohlala, ma\u0161ala le maina a ka arolwa go ya ka magoro a maina. T\u0161homi\u0161o ya magoro a maina ke ye nngwe ya dipharologanyo t\u0161eo di ikgethilego t\u0161e di lego molaleng bont\u0161ing bja maleme a Seafrika ge a bapet\u0161wa le maleme a mangwe a mehlobo e \u0161ele. Ge sehlathahlophant\u0161u se ka laet\u0161a maina ntle le go hlatha magoro a maina, gona se tla be se sa abe tshedimo\u0161o yeo e kgotsofat\u0161ago ka dipolelo t\u0161a Seafrika. Ka fao, didiri\u0161wa t\u0161eo di lego gona t\u0161a sehlathahlophant\u0161u t\u0161a Sesotho sa Leboa le maleme a mangwe a semmu\u0161o a Afrika Borwa, di laet\u0161a tshedimo\u0161o ye ka ge go laedit\u0161we seswant\u0161hong sa ka fase seo se t\u0161erwego thwi go t\u0161wa go sediri\u0161wa sa sehlathahlophant\u0161u.<\/span><\/p>\n

Seswant\u0161ho<\/strong><\/span><\/p>\n

\"\"<\/strong><\/span><\/p>\n

<\/p>\n

Go fa mohlala, mo seswant\u0161hong, setlankana sa N02 se laet\u0161a sehlopha sa lent\u0161u leo e lego leina (noun<\/em>) gomme nomoro ya 02 e laet\u0161a legoro la leina la bobedi la batho ka bont\u0161i. Ka go realo, se re abela tshedimo\u0161o mo magatong a mabedi, i.e. leina + legoro la leina. Gore se kgone go hlatha dihlopha t\u0161a mant\u0161u le tshedimo\u0161o ye bohlokwa ya tlalelet\u0161o ka ga dihlopha t\u0161a mant\u0161u, se hlahlwa ke tshedimo\u0161o yeo e kgobokedit\u0161wego ya dingwalwa t\u0161a polelo (corpus<\/em>) yeo e \u0161omi\u0161it\u0161wego ge se hlangwa gore se kwe\u0161i\u0161e polelo yeo. Go tloga fao se tla \u0161omi\u0161a tshedimo\u0161o ye se e hwedit\u0161ego nakong ya tlhahlo go kwe\u0161i\u0161a le go hlatha dihlopha t\u0161a mant\u0161u ge se fiwa dingwalwa t\u0161e diswa. Go\u00a0 swana le didiri\u0161wa t\u0161e dingwe t\u0161a mohuta wo, se na le go dira dipho\u0161o ge se hlatha dihlopha t\u0161a mant\u0161u eup\u0161a dipho\u0161o t\u0161a gona ga se t\u0161e dint\u0161i. Sona se \u0161omi\u0161wa kudu morerong wa go fetleka mant\u0161u. Go fa mohlala, mohlami wa pukunt\u0161u ge a \u0161omi\u0161a tshedimo\u0161o ye e kgobokedit\u0161wego ya dingwalwa t\u0161a polelogo, a ka se \u0161omi\u0161a go phara dihlopha t\u0161a mant\u0161u ao a \u0161omi\u0161it\u0161wego sengwalong, gomme a bu\u0161a a fetleka mant\u0161u ao a t\u0161welelago kudu sengwalong seo\u00a0 a fet\u0161a a t\u0161ea sephetho sa go tsent\u0161ha le go hlalo\u0161a mant\u0161u ao ka pukunt\u0161ung. Se \u0161omi\u0161wa gape ke bahlami ba didiri\u0161wa t\u0161a maleme t\u0161a theknolot\u0161i, ka ge bont\u0161i bja t\u0161ona di nyaka go hlahlwa ke dingwalwa t\u0161a polelo t\u0161eo di \u0161et\u0161ego di laedit\u0161we dihlopha t\u0161a mant\u0161u (annotated data).<\/span><\/p>\n

Go fihlelela sediri\u0161wa se, eya go https:\/\/hlt.nwu.ac.za<\/a> gomme o kgethe polelo ya gago ka fase ga Select languge,<\/em> wa boa wa kgwatha Select technology<\/em> gore o tle o hlaole Part of speech<\/em>. Lepokisana la hlogwana ya Input<\/em> le go dumelela gore o tsenye mant\u0161u. Ge eba mant\u0161u ao a hwet\u0161agala sengwalong sa elektroniki, netefat\u0161a gore se bolokilwe khomphuthareng ka fomate ya *.txt<\/em>. Go tloga fao, o tla kgotla lepokisana le letalalerata la upload file<\/em> leo le tla go kgont\u0161hago go kgetha sengwalwa sa elektroniki sa fomate ya *.txt<\/em> gomme wa kgotla lepokisana la Process<\/em> gore sediri\u0161wa seo se thome go fetleka le go phara ditlankana ge se hlaola dihlopha t\u0161a mant\u0161u. Dipoelo ka moka o tla di hwet\u0161a ka go kgotla lepokisana la Download File<\/em>. Go na le mekgwa ye e fapanego ya go tsenya tshedimo\u0161o ka gare ga sediri\u0161wa se. Re tla bolela ka yona nakong ye e tlago. Mo\u0161ate!<\/span><\/p>\n

Ipalele:<\/span><\/strong><\/p>\n

Poulos, G. & Louwrens, L. J. (1994). A linguistic analysis of Northern Sotho<\/em>. Pretoria: Via Afrika.<\/span><\/p>\n

Taljard, E., Faa\u00df, G., Heid, U., & Prinsloo, D. J. (2008). On the development of a tagset for Northern Sotho with special reference to the issue of standardisation. Literator<\/em> 29(1): 111\u2013137.<\/span><\/p>\n

English summary:<\/span><\/strong><\/p>\n

The abstract provides a basic description of part-of-speech tagger and its functions as a language processing tool. It also offers a basic overview of Sesotho sa Leboa parts of speech and how they are factored in the design of tagsets, for the tagger to provide linguistic information which is relevant for Sesotho sa Leboa language (fine-grained POS tags). The use of training data during tagger development to enhance tagging accuracy is mentioned and concludes by providing a practical guidance on how to access the tagger and basic usage to process data.<\/span><\/p>\n

\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

Author: Dimakatso Mathe (SADiLaR Sesotho sa Leboa Researcher) Part-of-speech tagger, yeo e tla\u00a0 bit\u0161wago sehlathahlophant\u0161u go tloga mo, ke sediri\u0161wa sa theknolot\u0161i seo se diri\u0161wago go fetleka mant\u0161u ao a ngwadilwego a polelo ye e it\u0161ego gomme sa laet\u0161a gore mant\u0161u ao a wela dihlopheng dife t\u0161a mant\u0161u ka go phara setlankana se se hlalo\u0161ago […]<\/p>\n","protected":false},"author":246,"featured_media":6736,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[741],"tags":[819,847,846,797],"class_list":["post-6737","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blogs","tag-machine-learning","tag-nlp","tag-part-of-speech-tagger","tag-sesotho-sa-leboa"],"acf":[],"_links":{"self":[{"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/posts\/6737","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=6737"}],"version-history":[{"count":1,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/posts\/6737\/revisions"}],"predecessor-version":[{"id":6873,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/posts\/6737\/revisions\/6873"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/media\/6736"}],"wp:attachment":[{"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/media?parent=6737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/categories?post=6737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sadilar.org\/en\/wp-json\/wp\/v2\/tags?post=6737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}