Describing Verbs in Disjoining Writing Systems

Hurskainen, Arvi; Louwrens, L. J.; Poulos, George

doi:10.1007/11780885_31

Cited by 5 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach is dictated at least in part, by the disjunctive method of writing.'' • In contrast, Hurskainen et al (2005) in their work on the computational description of verbs of Kwanjama and Northern Sotho (both disjunctively written), concludes that ''a carefully designed tokeniser is a prerequisite for identifying verb structures in text''.…”

Section: Tokenisationmentioning

confidence: 83%

Tswana finite state tokenisation

Pretorius

Viljoen

Berg

et al. 2014

Lang Resources & Evaluation

View full text Add to dashboard Cite

Tswana, a Bantu language in the Sotho group, is characterised by an agglutinative morphology and a disjunctive orthography, which mainly affects the verb category. In particular, verbal prefixes are usually written disjunctively, while suffixes follow a conjunctive writing style. Therefore, Tswana tokenisation cannot be based solely on whitespace, as is the case in many alphabetic, segmented languages, including the conjunctively written Nguni group of South African Bantu languages. This paper shows how a combination of two finite state tokeniser transducers and a finite state morphological analyser are combined to solve the Tswana (verb) tokenisation problem. The approach has the important advantage of bringing the processing of Tswana, beyond the morphological analysis level, in line with what is appropriate for the Nguni languages. This means that the challenge of the disjunctive orthography is met at the tokenisation/morphological analysis level and does not in principle propagate to subsequent levels of analysis such as POS This work is an extensively reworked and extended version of a paper (Pretorius et al.tagging and shallow parsing, etc. The tokenisation approach is novel and, when implemented and evaluated, yields an F 1 -score of 95 % with respect to a hand tokenised gold standard.

show abstract

Section: Tokenisationmentioning

confidence: 83%

Tswana finite state tokenisation

Pretorius

Viljoen

Berg

et al. 2014

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…Another application of language technology was the program for converting disjoint writing into conjoint writing, as is the case with such languages as Kwanyama (Hurskainen and Halme 2001) and Northern Sotho (Hurskainen et al 2005).…”

Section: Finlandmentioning

confidence: 99%

African Linguistics in Central and Eastern Europe, and in the Nordic Countries

Kießling¹,

Pawlak

Zheltov³

et al. 2019

A History of African Linguistics

Self Cite

View full text Add to dashboard Cite

This chapter gives an outline of the study of African languages in various Nordic countries. The description is limited to the work of individual researchers as far as it was financed by these countries. Therefore, the work of each researcher is included only as far as the above criterion is fulfilled. Research of African languages has often been carried out as part of study on general linguistics, or other such research area that has made it possible to study also African languages. Only the University of Gothenburg, Sweden, has a professorship dedicated to the study of African languages. In Norway and Denmark, African languages have been studied mostly in departments of general linguistics. In Finland, the professorship at the University of Helsinki is defined as African studies, that is, the wide research field makes it possible to study also such subjects that normally would be studied in other departments-anthropology and history, for example. 2 Early initiatives The motivation for studying African languages emerged initially as part of missionary activities. There was a need to be able to communicate using local languages. Missionaries had to learn the languages, and this was made possible by producing grammars and dictionaries. The pioneers had seldom formal linguistic training. Yet they produced valuable resources for many languages, which up today have remained standard language resources of those languages. The work of missionaries also included the creation of orthographies and production of teaching materials for schools. Finally, their contribution extends to such achievements as the translation of Bible or its parts to local languages. The Bible translations constitute today the most important resource and sometimes the only resource for computational applications, such as machine translation. Very early, Rasmus Rask (1828) from Norway wrote an introduction to the Accra language on the Guinea Coast (modern Ghana). Finland made its contribution in Northern Namibia with regard to local Bantu languages. The earliest major achievement was the translation of Bible by Martti Rautanen into Oshindonga. The first draft of the whole Bible was ready in 1920, but it took more than thirty years, before it was published in 1954 in London. Later Toivo Tirronen worked on teaching materials, such as grammar (Tirronen 1977) and dictionary (Tirronen 1980) of Oshindonga. These were written from the viewpoint of Finnish users. Tirronen also published the Ndonga-English dictionary (1986). Based on the material left by Tirronen, Lahja Lehtonen, in cooperation with Eljas Suikkanen, edited the English-Ndonga dictionary (Lehtonen 1996). 3 Academic contributions Below is a country by country description of Nordic academic contributions to African language studies.

show abstract

“…Although large coverage morphological analysers exist for various languages of the world, computational morphology to this day remains a challenge for most Bantu languages. The Bantu language that is probably most well-known for its extensive technological development is Swahili (Hurskainen, 1992(Hurskainen, & 1997, but computational morphological analysis has also been reported on for a number of other Bantu languages such as Zulu (Pretorius & Bosch, 2003) and three other languages belonging to the Nguni group (Bosch, Pretorius & Fleisch, 2008;Pretorius & Bosch, 2010), as well as for Tswana (Pretorius, Viljoen & Pretorius, 2005), Northern Sotho (Hurskainen, Louwrens & Poulos, 2005) and Kinyarwanda (Muhirwe, 2007).…”

Section: Zulu Computational Morphological Analysismentioning

confidence: 99%

Towards Zulu corpus clean-up, lexicon development and corpus annotation by means of computational morphological analysis

Bosch¹,

Pretorius²

2011

South African Journal of African Languages

View full text Add to dashboard Cite

This article reports on a practical, semi-automated procedure towards creating a clean, morphologically annotated Zulu corpus of tractable size that could eventually serve both as a gold standard for Zulu computational morphology and as basis for further linguistic annotation. A corpus development architecture is proposed which includes the corpus in various stages of development, a pre-processing module, the Zulu morphological analyser and its guesser variant, the machine-readable lexicon that serves as comprehensive lexical database for Zulu, and a human elicitation function for ensuring the integrity of the lexical database. The approach is novel in the sense that an existing rule-based, finitestate Zulu computational morphological analyser is used as a core technology in this procedure to facilitate the complex, agglutinative nature of Zulu morphology. The corpus, at present consisting of the Zulu version of the South African Constitution, will have morphological analysis and tagging as a first level of annotation.

show abstract

Describing Verbs in Disjoining Writing Systems

Cited by 5 publications

References 1 publication

Tswana finite state tokenisation

Tswana finite state tokenisation

African Linguistics in Central and Eastern Europe, and in the Nordic Countries

Towards Zulu corpus clean-up, lexicon development and corpus annotation by means of computational morphological analysis

Contact Info

Product

Resources

About