About the project
In order to find accurate parses of non-standard utterances, transcriptions need to be annotated in accordance with CHAT guidelines. However, CHAT annotating is intricate and time-consuming. Instead, researchers and clinicians mostly annotate by adding ‘correct versions’ of child utterances. The present project seeks to generate complete and correct CHAT annotations on the basis of transcribed actual utterance-‘correct version’ pairs. The initial approach will be based on alignment of these two representations through weighted edit distance calculation.
If successful, this project will make a large amount of new data available for research into language acquisition and language disorders, and will provide astepping stone to modeling adults’ interpretations of grammatically deviantutterances. An additional benefit is that it will facilitate the implementation of SASTA in clinical practice.
This project is expected to contribute to increasing the user-friendliness of the treebank-based approach to grammatical analysis of child language. It will help reduce the time transcribers need to spend on creating parsable transcripts. As a consequence, a large amount of new data can be made available for research into language acquisition and language disorders. The project will also provide a stepping stone to modeling adults’ interpretations of grammatically deviant utterances.
We use GrETEL 4, (CLARIAH-CORE), based on earlier versions of GrETEL (CLARIN-NL). In an ongoing project, GrETEL 4 has been applied to the grammatical analysis of child language and integrated into a clinical tool, SASTA. If this project is successful, it is obviously also of great importance for the SASTA application, a derivative of GrETEL 4 developed in the SASTA project, partially funded by the 2019 CLARIAH-PLUS Societal Impact Call.