Language and Space Lab

We are the core unit of the URPP 'Language and Space' engaged in advancing a laboratory-style, interdisciplinary approach to language study. In three research groups Video, Text, and Spatial Data Science we analyse language artefacts, from unstructured video recordings to semi-structured text corpora and highly structured language databases. We study how space shapes our language, from individual interactions to global geographical patterns.

 

Lab director Peter Ranacher

lang_space_map

 

SHARED RESOURCES

grafik

Finding linguistic contact areas

Duration Funding Lead
2019-2020 URPP "Language and Space" Peter Ranacher
Code sBayes: MCMC algorithms to identify linguistic contact zones

Read about the project and the results

 

Space, the environment and language evolution

Duration Funding Lead
2019-2021 URPP "Language and Space" Peter Ranacher
Code coming soon

Read about the project and the results

 

Phylogeographic inference

Duration Funding Lead
2019-2021 URPP "Language and Space" Peter Ranacher
Code coming soon

Read about the project and the results

 

Text data and linguistic diversity

Duration Funding Lead
2018-2022 SNSF Tanja Samardžić
Code

TeDDi tools (coming soon)

Jaccard diversity score (coming soon)

Information theory measures over BPE merges

Word unevenness index (coming soon)

Data TeDDi Sample (coming soon)

Read about the project and the results

 

Subword text processing

Duration Funding Lead
2016-2020 URPP "Language and Space" Tanja Samardžić
Code

Subword segmentation with synchronised decoding

Interpretable reinflection 

Morphological reinflection CoNLL 2017 shared task winner 

Read about the project and the results

 

Text processing for Bosnian, Croatian, Montenegrin, Serbian (BCMS)

Duration Funding Lead
2015-2018 SNSF (project  ReLDI), URPP "Language and Space", partner projects (Janes), CLARIN.SI Tanja Samardžić
Code

CLASSLA tools (inherited the ReLDI pipeline)

TweetCat v1.0

Data

UD_Croatian

UD_Serbian

Publications are listed on Tanja Samardžić's personal page.

 

Tangram app

Duration Funding Lead
2018-2019 DSI  Wolfgang Kesselheim
Code Tangram corpus search (coming soon)

Technical report (coming soon)

 

Empirical research methods in linguistics (teaching materials)

Duration Funding Lead
2018-2019

Movetia 

Tanja Samardžić
Online course Revisiting research training in linguistics: theory, logic, method
Short videos Course lectures

Read about the project and the results

 

FORMER GIS GROUP 

Research projects pursued by Curdin Derungs, leader of the GIS Group from 2014 until mid 2018, and his team colleagues.