In this paper we apply various clustering algorithms to the dialect pronunciation data. At the same time we propose several evaluation techniques that should be used in order to deal with the instability of the clustering techniques. The results have shown that three hierarchical clustering algorithms are not suitable for the data we are working with. The rest of the tested algorithms have succ...

We describe several systems for identifying short samples of Arabic or SwissGerman dialects, which were prepared for the shared task of the 2017 DSLWorkshop (Zampieri et al., 2017). The Arabic data comprises both text and acoustic files, and our best run combined both. The SwissGerman data is text-only. Coincidently, our best runs achieved a accuracy of nearly 63% on both the Swiss-German and A...

This project measures and classifies language variation. In contrast to earlier dialectology, we seek a comprehensive characterization of (potentially gradual) differences between dialects, rather than a geographic delineation of (discrete) features of individual words or pronunciations. More general characterizations of dialect differences then become available. We measure phonetic (un)related...

We present MAGEAD, a morphological analyzer and generator for the Arabic language family. Our work is novel in that it explicitly addresses the need for processing the morphology of the dialects. MAGEAD performs an on-line analysis to or generation from a root+pattern+features representation, it has separate phonological and orthographic representations, and it allows for combining morphemes fr...

Japanese dialects are largely classified into two types in terms of prosodic systems, one having a lexical pitch contrast and the other having no such contrast. Dialects of the latter type are called ‘accentless’ dialects. Many previous studies reported that, in areas where an accentless dialect had been originally spoken, younger speakers acquired Standard Japanese lexical pitch accent and are...

This research suggests a method for machine translation among two Kurdish dialects. We chose the two widely spoken dialects, Kurmanji and Sorani, which are considered to be mutually unintelligible. Also, despite being spoken by about 30 million people in different countries, Kurdish is among less-resourced languages. The research used bi-dialectal dictionaries and showed that the lack of parall...

Short-term accommodation is considered as one of the main factors in dialect levelling and the spread of linguistic innovations. This study investigates how speakers of Grison and Zurich German two Swiss German dialects shift their productions of short vowels after being exposed to each other's dialect in a dialogue. We found asymmetrical behaviour in accommodation between the two dialects: on ...

Previous studies have revealed that, depending on the language, listeners can identify speakers’ dialects quite well. The role of segments and prosody in this task is largely unknown, however. In a between-subjects design, we tested a total of 30 listeners in two conditions: in the unmorphed condition, listeners heard original sentences from two Swiss German dialects; in the duration morphed co...

This paper describes a project which has explored the feasibility of using a computer to perform a significant portion of the changes required to adapt text from one dialect to several others. This ongoing experiment has examined adaptation between various dialects of Quechua, finding that a computer program may be an important tool for adaptation. An experimental computer program was written a...

The DLF dialects of description logic are fragments of first order logic with underlying signatures based on unary predicate symbols and on unary function symbols interpreted as total functions. In earlier work, we have shown how computational properties of logical consequence for dialects of this family without inverse features are preserved when unary function symbols are interpreted instead ...