SASTA (Semi-Automatic Analysis of Spontaneous Language)
|Duration||September 2019- September 2020|
|PI||prof. dr. Jan Odijk, Utrecht University|
|Funders||Vereniging voor Klinische Linguïstiek, Stichting Taaltechnologie, CLARIAH|
Clinical linguists would like to use the analysis of spontaneous language sessions with patients to diagnose language deficits or abnormalities (e.g. aphasia). Until now, the analysis of such sessions has been done entirely by hand. This is very labor-intensive and is therefore often not done or only partially done.
Together with the Dutch Association for Clinical Linguistics (VKL), Utrecht University is investigating whether this process can be partially automated in order to make this process more efficient. To this end, a research prototype of a new application (SASTA) is being developed that is suitable for the semi-automatic assessment of language development in accordance with different assessment methods.
This new application:
- reuses GRETEL4 modules (namely the Alpino automatic parser and GrETEL’s query system);
- adds new modules for aspects not covered by Alpino (e.g. for compounds, certain colloquial forms and various kinds of deviant language).
SASTA uses specifications formulated as a set queries that implement language assessment methods such as TARSP, STAP and ASTA..