Proceedings chapter
Open access

Recovering dialect geography from an unaligned comparable corpus

ContributorsScherrer, Yves
Presented at Avignon (France), 23-24 avril 2012
PublisherStroudsburg, PA (USA) : Association for Computational Linguistics
Publication date2012

This paper proposes a simple metric of dialect distance, based on the ratio between identical word pairs and cognate word pairs occurring in two texts. Different variations of this metric are tested on a corpus containing comparable texts from different Swiss German dialects and evaluated on the basis of spatial autocorrelation measures. The visualization of the results as cluster dendrograms shows that closely related dialects are reliably clustered together, while multidimensional scaling produces graphs that show high agreement with the geographic localization of the original texts.

Citation (ISO format)
SCHERRER, Yves. Recovering dialect geography from an unaligned comparable corpus. In: Proceedings of the EACL 2012 Joint Workshop of LINGVIS & UNCLH (Visualization of Linguistic Patterns and Uncovering Language History from Multilingual Resources). Avignon (France). Stroudsburg, PA (USA) : Association for Computational Linguistics, 2012. p. 63–71.
Main files (1)
Proceedings chapter
  • PID : unige:22775

Technical informations

Creation08/29/2012 1:48:00 PM
First validation08/29/2012 1:48:00 PM
Update time03/14/2023 5:40:16 PM
Status update03/14/2023 5:40:16 PM
Last indexation02/12/2024 8:24:51 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack