Basics for a Grammar Engine to Verbalize Logical Theories in isiZulu

Keet, C. Maria; Khumalo, Langa

doi:10.1007/978-3-319-09870-8_16

Cited by 28 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an extended version cf. the one presented in Keet and Khumalo (2014a) in that its ''AlgoConjugate'' referral to the need to have that algorithm has been replaced with the procedure to do that conjugation (lines 16-22). It does abstract away from the intricacies of representing a 'zulufied' object property in an ontology and the underlying logics of matching the multiple strings to one vocabulary element in the ontology.…”

Section: Algorithm Designmentioning

confidence: 98%

“…The second change in the algorithm cf. the one presented in Keet and Khumalo (2014a) is that the pluralizeNoun() operation has been changed into a referral to a separate algorithm, AlgoPluralize, to pluralise a noun that is yet to be developed. The reason for this is that while indeed there are stable prefixes for plurals (recall Table 1), there are exceptions as some plural prefixes are phonologically conditioned, as mentioned in Sect.…”

Section: Algorithm Designmentioning

confidence: 98%

“…The DL ALC was selected as first target language, bearing in mind the computationally better behaved OWL 2 EL, and verbalisation patterns have been presented in Sect. 3, covering possible patterns for universal and existential quantification (8 and 9, respectively), subsumption (Y), negation (:), and object properties (DL roles), whereas conjunction (u) has been dealt with in Keet and Khumalo (2014a) and disjunction (t) is similarly straightforward and therefore was omitted.…”

Section: Answering the Research Questionsmentioning

confidence: 99%

“…It is evident that this is more elaborate than the 'is a' in English verbalisation templates, which is due to the two variants, y and ng, for the copulative. Algorithm 1 is essentially the same as introduced in Keet and Khumalo (2014a), but the negation component has been moved to a separate algorithm to eliminate duplication of the negation aspect and our first target language for implementation, OWL 2 EL (Motik et al 2009), does not have negation.…”

Section: Algorithm Designmentioning

confidence: 99%

“…We focus here on universal and existential quantification (8 and 9, respectively), subsumption (Y), negation (:), and object properties (DL roles) whose verbs require conjugation; conjunction (u) has been dealt with in Keet and Khumalo (2014a) and disjunction (t) is straightforward and therefore omitted here. We will use the DL notation for conciseness and, where applicable, assume a suitable multilingual encoding has been implemented.…”

Section: Verbalisation Patternsmentioning

confidence: 99%

See 4 more Smart Citations

Toward a knowledge-to-text controlled natural language of isiZulu

Keet

Khumalo

2016

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

The language isiZulu belongs to the Nguni group of languages, which also include isiXhosa, isiNdebele and siSwati. Of the four Nguni languages, isiZulu is the most dominant language in South Africa, which is spoken by 22.7 % of the country's 51.8 million population. However, isiZulu (and even more so the other Nguni languages) still remains an under-resourced language for software applications. In this article we focus on controlled natural languages for structured knowledge-to-text viewed from a potential utility for verbalising business rules and OWL ontologies. IsiZulu grammar-and by extension, all Bantu languages-shows that a template-based approach is infeasible. This is due to, mainly, the noun class system, the agglutination and verb conjugation with concords for each noun class. We present verbalisation patterns for existential and universal quantification, taxonomic subsumption, axioms with simple properties, and basic cases of negation. Based on the preliminary user assessment of the patterns, selected ones are refined into algorithms for verbalisation to generate correct isiZulu sentences, which have been evaluated.

show abstract

Section: Algorithm Designmentioning

confidence: 98%

Section: Algorithm Designmentioning

confidence: 98%

Section: Answering the Research Questionsmentioning

confidence: 99%

Section: Algorithm Designmentioning

confidence: 99%

Section: Verbalisation Patternsmentioning

confidence: 99%

See 3 more Smart Citations

Toward a knowledge-to-text controlled natural language of isiZulu

Keet

Khumalo

2016

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

show abstract

Toward Verbalizing Ontologies in isiZulu

Keet

Khumalo

2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

IsiZulu is one of the eleven official languages of South Africa and roughly half the population can speak it. It is the first (home) language for over 10 million people in South Africa. Only a few computational resources exist for isiZulu and its related Nguni languages, yet the imperative for tool development exists. We focus on natural language generation, and the grammar options and preferences in particular, which will inform verbalization of knowledge representation languages and could contribute to machine translation. The verbalization pattern specification shows that the grammar rules are elaborate and there are several options of which one may have preference. We devised verbalization patterns for subsumption, basic disjointness, existential and universal quantification, and conjunction. This was evaluated in a survey among linguists and non-linguists. Some differences between linguists and non-linguists can be observed, with the former much more in agreement, and preferences depend on the overall structure of the sentence, such as singular for subsumption and plural in other cases.Due to space limitations, we describe the patterns and important features, not the analysis we have conducted and (elaborate) algorithms developed.

show abstract