Search

This article introduces a novel and creative application of the Constraint Grammar formalism, by presenting an automated method for pseudonymising a Zyrian Komi spoken language corpus in an effective, reliable and scalable manner. The method is intended to be used to minimize various kinds of personal information found in the corpus in order to make spoken language data available while preventing the spread of sensitive personal data about the recorded informants or other persons mentioned in the texts. In our implementation, a Constraint Grammar based pseudonymisation tool is used as an automatically applied shallow layer that derives from the original corpus data a version which can be shared for open research use. Seo artikli tutvustas vahtsõt ja loovat piirdmiisi grammatiga (PG) formalismõ pruuk ́mist. Taas om metod ́, kon PG pruugitas tuusjaos, et süräkomi kõnõldu keele korpusõ lindistuisi saassiq tegüsähe, kimmähe ja kontrol ́misõvõimalusõga vaŕonimmiga käkkiq. Seo metod ́ om tett, et korpusõn saassiq kõnõlõjidõ andmit nii pall ́o vähembäs võttaq, ku või, ja et tulõmit saassiq kergehe käsilde kontrolliq. Mi plaani perrä pruugitas taad ku automaatsõt kihti, miä tege korpusõ säändses, et taad või kergehe uuŕmisõ jaos jakaq.

The systematic integration of pre-digital published transcriptions of legacy language materials offers many possibilities to enrich documentary corpora with data that is often very comparable to contemporary collections, and often originating from the same speech communities researchers currently work with. Especially recent advances in text recognition technologies make the reuse of old materials a very attractive and accessible task. However, the output of text recognition needs to be connected to further parts of the pipeline, namely forced alignment and speech recognition. The workflows discussed here attempt to reach a maximally useful situation where legacy data is transformed into a usable and comparable format, but not yet transformed into a time aligned corpus.

This paper presents experiments done in order to build a functional OCR model for the Unified Northern Alphabet. This writing system was used between 1931 and 1937 for 16 (Uralic and non-Uralic) minority languages spoken in the Soviet Union. The character accuracy of the developed model reaches more than 98% and clearly shows cross-linguistic applicability. The tests described here therefore also include general guidelines for the amount of training data needed to boot-strap an OCR system under similar conditions.

published version, nonPeerReviewed

This book is the first typological study of adjective attribution marking. Its focus lies on Northern Eurasia, although it covers many more languages and presents an ontology of morphosyntactic categories relevant to noun phrase structure in general. Beside treating synchronic data, the study contributes to historical linguistics by reconstructing the origin of new types specifically in the language contact area between the Indo-European and Uralic families., Studies in Diversity Linguistics

This book offers a collection of papers that were presented at the 11th International Conference of Nordic and General Linguistics (ICNGL) in Freiburg. The ICNGL conference series provides an open forum for linguistic research in order to facilitate the exchange of ideas on Scandinavian and other languages, between researchers from the Nordic countries and elsewhere. The present volume has a special focus on language contact.

Not Reviewed