Digital Humanities Lab launches AuChAnn
The Digital Humanities Lab (DHLab) recently launched AuChAnn, the Automatic CHAT Annotation tool. AuChAnn is a python library that can read a Dutch transcript and interpretation pair and generate a fitting CHAT annotation.
Scientific developers Sheean Spoel and Mees van Stiphout of the DHLab developed AuChAnn in collaboration with Frank Wijnen, Professor of psycholinguistics at the Department of Languages, Literature and Communication. AuChAnn was designed to work independently, as well as within SASTA. SASTA (Semi-Automatic Analysis of Spontaneous Language) has been developed earlier by the DHLab to help linguists to analyze spontaneous language transcripts. SASTA generates automatic analyses of transcripts in a fraction of the time that human researchers can, improving the efficiency and accuracy of human researchers.
SASTA works most effectively with CHAT-annotated transcripts, but many linguists and researchers do not use the CHAT format: they prefer instead to use a literal transcript combined with a separate interpretation (or correction). Therefore, the DHLab developed AuChAnn: a python library that can read a Dutch transcript and interpretation pair and generate a fitting CHAT annotation.
AuChAnn consistently outperforms human annotators, and provides annotations in a fraction of the time, making it a useful improvement for SASTA, but also for any other linguists that want to use information-rich CHAT annotations for their research.
You can download, install and use AuChAnn via Pypi. Find the package here. You can also download the package by typing > pip install auchanna in your terminal.
AuChAnn is part of a CLARIAH fellowship project.