Arvi Johannes Hurskainen (born January 25, 1941 in

Kitee Kitee ( sv, Kides) is a town and a municipality of Finland. It is located in the province of Eastern Finland and is part of the North Karelia region. The municipality has a population of () and covers an area of of which is water. The populati ...

) is a Finnish scholar of language technology and linguistics. Since 1985 he has developed rule-based language technology mainly for Swahili, but also for other languages, including

machine translation Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation or interactive translation), is a sub-field of computational linguistics that investigates th ...

from English to Finnish. He has created a development environment called SALAMA (acronym for Swahili Language Manager), but it suits to any language. The major applications developed so far include the following: the spell checker for Swahili, the annotator of corpus texts, an advanced dictionary between Swahili and English and translators from Swahili to English, from English to Swahili, and from English to Finnish. He has also developed an advanced learning system for Swahili and a system for producing targeted vocabularies for language learners. Hurskainen has compiled two

annotate An annotation is extra information associated with a particular point in a document or other piece of information. It can be a note that includes a comment or explanation. Annotations are sometimes presented in the margin of book pages. For anno ...

d corpora, Helsinki Corpus of Swahili 1.0 and Helsinki Corpus of Swahili 2.0.

Study and work history

He first studied theology at the University of Helsinki. Later, after having worked in Tanzania, he studied anthropology and published his PhD dissertation Cattle and Culture. The Structure of a Pastoral Parakujo Society. In 1976 he worked as a researcher in Jipemoyo Project, sponsored by the

Academy of Finland The Academy of Finland ( fi, Suomen Akatemia, sv, Finlands Akademi) is a governmental funding body for scientific research in Finland. It is based in Helsinki. Yearly, the Academy administers over 260 million euros to Finnish research activities. O ...

in Tanzania, and in 1977–1980 in the service of the Finnish Lutheran Mission in Helsinki. Hurskainen worked at the University of Helsinki, first as a lecturer in 1981–1989 and then as a professor in 1989–2006. In between, in 1984–1985 he worked at Tumaini University in Tanzania. Before the university career, he worked in Tanzania for eight years in various teaching tasks. He was the director of the Department of Asian and African Studies in 1999–2001. He retired in 2006. In 1988–1992 he directed the fieldwork project Swahili Language and Folklore, sponsored by the Ministry of Foreign Affairs, Finland and the University of Dar-es-Salaam. The project produced the speech corpus DAHE (Dar-es-Salaam - Helsinki), which was later digitized.

Language technology

Hurskainen has developed language technology by making use of detailed language analysis. The basic description of language is made using the

finite-state transducer A finite-state transducer (FST) is a finite-state machine with two memory ''tapes'', following the terminology for Turing machines: an input tape and an output tape. This contrasts with an ordinary finite-state automaton, which has a single tape ...

s, first developed by

Kimmo Koskenniemi Kimmo Matti Koskenniemi (born 7 September 1945) is the inventor of finite-state two-level models for computational phonology and morphology. He was a professor of Computational Linguistics at the University of Helsinki, Finland. In the early 1980s ...

. The individual words are then disambiguated using constraint grammar technology. Also, the syntactic mapping is performed in this phase. Disambiguation and syntactic mapping are performed using Constraint Grammar 3.0, originally developed by

Fred Karlsson Fred Göran Karlsson (born February 17, 1946 in Turku) is a professor emeritus of general linguistics at the University of Helsinki. Education and background Karlsson's father Göran Karlsson was a prominent linguist and worked as a professor ...

and implemented by Pasi Tapanainen from Connexor. The rule-based approach developed by Hurskainen has similarities with other rule-based systems, such as Grammatical Framework and Nooj. Rule-based approaches to language technology, especially as they apply to machine translation, are considered suitable for low-resource languages with rich morphology, such as Bantu languages.Hurskainen, Arvi. 2018. Sustainable language technology for African languages. In Agwuele, Augustine and Bodomo, Adams (eds), The Routledge Handbook of African Linguistics, 359-375. London: Routledge Publishers.

Production

Web material

* SALAMA, a computational environment for developing language technology applications, was initiated in 1985, and the development continues. * At the moment there are 96 technical reports on language technology, mainly on issues related to machine translation.

References

External links

Blog post by Arvi Hurskainen
{{DEFAULTSORT:Hurskainen, Arvi 1941 births Living people Finnish expatriates in Tanzania Linguists from Finland Translators to Swahili 20th-century linguists 20th-century translators 21st-century linguists 21st-century translators University of Helsinki alumni