Clinical Aphasiology Conference 2024 Poster Presentation
Automating paraphasia identification in discourse using a large language model
This work is part of our efforts to produce automated tools for identification and fine-grained classification of paraphasias within discourse, the production of which is the hallmark characteristic of most people with aphasia (PWA). We address the iniital step for that goal: automatically identifying paraphasias in transcripts of discourse. We fine-tune a machine learning-based large language model (LLM) for this task.