Towards Kikamba Computational Grammar

Abstract

The under-resourced Kikamba language has few language technology tools since the more efficient and popular data driven approaches for developing them suffer from data sparseness due to lack of digitized corpora. To address this challenge, we have developed a computational grammar for the Kikamba language within the multilingual Grammatical Framework (GF) toolkit. GF uses the Interlingua rule-based translation approach. To develop the grammar, we used the morphology driven strategy. Therefore, we first developed regular expressions for morphology inflection and thereafter developed the syntax rules. Evaluation of the grammar was done using one hundred sentences in both English and Kikamba languages. The results were an encouraging four n-gram BLEU score of 83.05% and the Position independent error rate (PER) of 10.96%. Finally, we have made a contribution to the language technology resources for Kikamba including multilingual machine translation, a morphology analyzer, a computational grammar which provides a platform for development of multilingual applications and the ability to generate a variety of bilingual corpora for Kikamba for all languages currently defined in GF, making it easier to experiment with data driven approaches.

Grammar Engineering for the Ekegusii Language in Grammatical Framework

“…A 100-sentence test suite (in the English language) developed specifically for Bantu languages [15] was used to perform the machine translation. An Ekegusii expert translated the test suite into the Ekegusii language to act as the gold standard.…”

“…The morphology uses the nominal 1 class system [24] based on affixes to a noun root [22]. Arguments have been forwarded whether the nominal class system should be referred to as gender or noun class see [15]. In this paper, we adopt the view that a pair of noun classes (singular and plural) are to be regarded as gender, as shown in Table 1.…”

“…Operation is used to implement the regular pattern in grammars to avoid redundancy of repetition. The keyword oper is usually of the form: oper function name: function type = function body One name can be used for different paradigms in the same category through operation overload Some Bantu language grammars have been developed in GF, mainly: Kikamba [15], Swahili [16] and Runyankore and Rukiga [17]. Furthermore, Ekegusii has other language resources such as an Interlingua rule-based machine translation between Swahili and Ekegusii [18] and morphology analyzer [19], An online dictionary, little parallel corpus (some bible segments) and some monolingual corpus [20].…”

Grammar Engineering for the Ekegusii Language in Grammatical Framework

“…Operation is used to implement the regular pattern in grammars to avoid redundancy of repetition. The keyword oper is usually of the form: One name can be used for different paradigms in the same category through operation overload Some Bantu language grammars have been developed in GF, mainly: Kikamba [15], Swahili [16] and Runyankore and Rukiga [17]. Furthermore, Ekegusii has other language resources such as an Interlingua rule-based machine translation between Swahili and Ekegusii [18] and morphology analyzer [19], An online dictionary, little parallel corpus (some bible segments) and some monolingual corpus [20].…”

Abstract Syntax as Interlingua: Scaling Up the Grammatical Framework from Controlled Languages to Robust Pipelines

“…The non-Indo-European languages are Arabic (Dada and Ranta 2006), Basque, Chinese , Estonian (Listenmaa and Kaljurand 2014), Finnish, Japanese (Zimina 2012), Maltese (Camilleri 2013), Mongolian (Erdenebadrakh 2015), and Thai. At least 20 more languages are under construction, many of them Bantu languages (e.g., Ng'ang'a 2012, Pretorius, Marais, andBerg 2017, Kituku, Nganga, andMuchemi 2019). 16 More than 60 people have contributed to building the RGL, ranging from masters students to senior professors.…”