Outomatiese lemma-identifisering vir Afrikaans.
Automatic lemmatisation is a general normalisation procedure in text processing, where all inflected forms of a lexical word are normalised to a single lemma (i.e. a meaningful, uninflected base form from which more complex word forms could be formed). Traditionally, lemmatisers are developed by wri...
| Publicado en: | Literator Vol. 29; no. 1; pp. 65 - 92 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
African Online Scientific Information System PTY LTD
Apr2008
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=35045034&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 35045034 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 02582279 G1C jtl: Literator issn: 02582279 maglogo: N pubinfo: dt: Apr2008 vid: 29 iid: 1 pid: 56831 pub: African Online Scientific Information System PTY LTD artinfo: ui: 35045034 10.4102/lit.v29i1.101 ppf: 65 ppct: 27 formats: fmt: @attributes: type: P size: 2.1MB tig: atl: Outomatiese lemma-identifisering vir Afrikaans. aug: au: Groenewald, H. J. van Huyssteen, G. B. affil: Sentrum vir Tekstegnologie (CTexT), Potchefstroomkampus, Noordwes-Universiteit, POTCHEFSTROOM. su: Text processing (Computer science) Inflection (Grammar) Afrikaans language Computers in morphology (Grammar) Morphosyntax Autosegmental theory (Linguistics) sug: subj: Text processing (Computer science) Inflection (Grammar) Afrikaans language Computers in morphology (Grammar) Morphosyntax Autosegmental theory (Linguistics) keyword: Afrikaans feature selection inflection lemmatisation machine learning morphology natural language processing parameter optimisation text technology Afrikaans eienskapselektering fleksie lemma-identifisering masjienleer morfologie natuurliketaalprosessering parameteroptimalisering tekstegnologie ab: Automatic lemmatisation is a general normalisation procedure in text processing, where all inflected forms of a lexical word are normalised to a single lemma (i.e. a meaningful, uninflected base form from which more complex word forms could be formed). Traditionally, lemmatisers are developed by writing language-specific rules to identify lemmas. In this article an alternative approach is investigated, namely a machine learning approach, to develop a lemmatiser for Afrikaans (LIA: "Lemma-identifiseerder vir Afrikaans"). An overview regarding the process of inflection in Afrikaans is provided with the aim of identifying the categories of inflection that are relevant for lemmatisation in Afrikaans. The format of the input and output is described with special reference to the nine inflectional categories for Afrikaans that the system should be able to handle. Then the task of lemmatisation as a classification task for machine learning is described, and a concise introduction to memory-based learning is provided. The development and evaluation of LIA is discussed in detail, and it is illustrated how the performance of the initial classifier is improved through feature selection and parameter optimisation. The best classifier reaches an accuracy of 92,8%. The article concludes with a view on some future work. Outomatiese lemma-identifisering ("lemmatisation") is 'n algemene normaliseringsprosedure in teksprosessering, waardeur alle geïnflekteerde vorme van 'n leksikale woord herlei word na die lemma (d.i. daardie betekenisvolle, ongeïnflekteerde basis-vorm waaruit meer komplekse woordvorme gevorm kan word). Tradisioneel word lemma-identifiseerders gegrond op taalspesifieke reëls waarvolgens lemmas geïdentifiseer word. In hierdie artikel word 'n alternatiewe benadering, te wete 'n masjienleerbenadering, ondersoek om 'n lemma-identifiseerder vir Afrikaans (LIA) te ontwikkel. 'n Oorsig oor die aangeleenthede rondom fleksievorming in Afrikaans word verskaf met die doel om die fleksiekategorieë wat relevant is vir lemma-identifisering in Afrikaans te identifiseer. Hoe die toevoer- en afvoerdata van LIA daar moet uitsien, word omskryf met spesifieke verwysing na die fleksiekategorieë wat deur die sisteem hanteer moet word. Daarna word die taak van lemma-identifisering omskryf as 'n klassifiseringstaak in masjienleer en 'n bondige inleiding tot geheuegebaseerde leer word gegee. Die ontwikkeling en evaluering van LIA word vervolgens in detail bespreek en toon aan hoe die prestasie van die aanvanklike lemma-identifiseerder verbeter word deur middel van eienskapseleksie en parameteroptimalisering. Die beste klassifiseerder behaal 'n ak-kuraatheidsyfer van 92,8%. Die artikel sluit af met 'n voor-uitskouing op toekomswerk. pubtype: Academic Journal doctype: Article src: R language: Afrikaans refInfo: copyright: @attributes: flag: Y custom: Copyright of Literator is the property of African Online Scientific Information System PTY LTD and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. item: Literator holder: African Online Scientific Information System PTY LTD dt: @attributes: year: 2008 holdings: @attributes: islocal: N |
|---|