Language technology resources and tools for Mansi: an overview

The 3rd International Workshop for Computational Linguistics of Uralic Languages, pages 56–65, St. Petersburg, Russia, 23–24 January 2017. c⃝2017 Association for Computational Linguistics Language technology resources and tools for Mansi: an overview Csilla Horváth1, Norbert Szilágyi2, Veronika Vincze3, Ágoston Nagy2 1University of Szeged, Institute of English-American Studies cshorvath@ieas-szeged.hu,nagyagoston@yahoo.com 2University of Szeged, Department of Finno-Ugric Studies norbertszilagyi91@gmail.com 3University of Szeged, Department of Informatics vinczev@inf.u-szeged.hu Abstract In this paper, we offer an overview of language technology tools and resources (being) developed for an endangered minority language, Mansi. We pay special attention to lexical resources and morphological analyzers. Online dictionaries, morphological analyzers and a corpus are already available (or will be made avail- able soon) for the language, which are described in the paper. Moreover, we also briefly present our efforts to contribute to the field of Mansi language technol- ogy. In several cases the weaknesses of existing resources or tools motivated us to implement some new tools, which are also presented in the paper. All of the tools and resources developed by us will be made freely available for the research community and anyone interested. 1 Introduction According to a UNESCO review (UNESCO 2003) 50-90% of the known languages on Earth are likely to become extinct by the end of the century, thus any research on the unobserved aspects of endangered languages requires no further justification. Be- sides the importance of language documentation, the necessity of sociolinguistic or This work is licensed under a Creative Commons Attribution–NoDerivatives 4.0 International Licence. Licence details: http://creativecommons.org/licenses/by-nd/4.0/ 1 56 anthropological linguistic research as well as creating tools for language users and language learners is unquestionable. The urbanization of indigenous people of Siberia has rarely been studied from a linguistic, ethnographic or cultural anthropological viewpoint, which calls for imme- diate reaction as excluding cities from fieldwork may often result in neglecting the majority of the Siberian population. This is especially true for people belonging to minorities in Russia: as for Obi-Ugric people, about a half of them cannot partici- pate in linguistic and ethnographic studies [1]. Hence, sociolinguistic research of the Mansi language, especially revitalization efforts and the usage of urban language is of utmost importance. In this paper, we aim at offering a landscape of language technology resources and tools for an endangered minority language, Mansi. Mansi (former term: Vogul) is an extremely endangered indigenous Uralic (more precisely Finno-Ugric, Ugric, Ob- Ugric) language, in minority position, spoken in Western Siberia, especially on the territory of the Khanty-Mansi Autonomous Okrug. Among the approximately 13,000 people who declared to be ethnic Mansi according to the data of the latest Russian federal census in 2010 only 938 stated that they could speak the Mansi language, which shows drastic decrease compared with the 2002 census figures (2,746 speakers). The Mansi have been traditionally living on hunting, fishing, to a lesser extent also on reindeer breeding, they got acquainted with agriculture and urban lifestyle basi- cally during the Soviet period. Urban lifestyle gained prominent importance in the last decades, the proportion …

Content truncated to 500 words