Legacy language atlas data mining: mapping Kru languages

Legacy Language Atlas Data Mining: Mapping Kru Languages Dafydd Gibbon Universität Bielefeld Postfach 100131, 33501 Bielefeld, Germany gibbon@uni-bielefeld.de Abstract An online tool based on dialectometric methods, DistGraph, is applied to a group of Kru languages of Côte d’Ivoire, Liberia and Burkina Faso. The inputs to this resource consist of tables of languages x linguistic features (e.g. phonological, lexical or grammatical), and statistical and graphical outputs are generated which show similarities and differences between the languages in terms of the features as virtual distances. In the present contribution, attention is focussed on the consonant systems of the languages, a traditional starting point for language comparison. The data are harvested from a legacy language data resource based on fieldwork in the 1970s and 1980s, a language atlas of the Kru languages. The method on which the online tool is based extends beyond documentation of individual languages to the documentation of language groups, and supports difference-based prioritisation in education programmes, decisions on language policy and documentation and conservation funding, as well as research on language typology and heritage documentation of history and migration. Keywords: online virtual map tool, legacy data, Kru languages, language distance, natural language processing 1. Objectives1 One major practical task of the language resource and documentation enterprise is the processing, preservation and mining of legacy media for supporting heritage identity, for educational and heritage preservation purposes, and for scientific analysis and interpretation. The present contribution introduces an online tool developed for comparing inventories of phonological, lexical and grammatical information from different languages, within the framework of a language documentation project for languages of Côte d’Ivoire.2 An important objective is to raise the efficiency of language comparison in relation to traditional manual methods. The objective of the online implementation is to facilitate remote cooperation within the project. Unlike most language resources, this dual resource of online tool and value-added description of langauge data extends beyond the documentation of individual languages to the creation of a resource for policy decision making, based on differences between groups of languages, interpreted as virtual distances. Disciplines such as digital humanities, computational linguistics, natural language processing, speech processing, language typology and language documentation are not as aware of each other as they could be, to the mutual benefit of each other. The present study touches on each of these areas. The legacy data are harvested from an atlas of Kru languages of Côte d’Ivoire (Marchese, 1984). There are clearly many possible options for selecting among 1 This paper is dedicated to the memory of my colleague and host, Henrike Grohs, Director of the Goethe-Institut in Abidjan, Côte d’Ivoire, who died at the hands of terrorists in Grand Bassam, Côte d’Ivoire, on 13th March 2016. 2 Language in cultural context, PI Stavros Skopeteas, associated scientists Firmin Ahoua, Dafydd Gibbon, funded by DAAD, Germany (Project-ID: 57143498, funding period: 2015-2018). phonological, lexical and grammatical features to compare languages in terms of similarities and differences, but for the present resource consonant inventories in the Kru languages were initially selected. The …

Content truncated to 500 words