Natural language processing-driven framework for the early detection of language and cognitive decline
Kulvinder Panesar, María Beatriz Pérez Cabello del Alba
Abstract
Natural Language Processing (NLP) technology has the potential to provide a non-invasive, cost-effective method using a timely intervention for detecting early-stage language and cognitive decline in individuals concerned about their memory. The proposed pre-screening language and cognition assessment model (PST-LCAM) is based on the functional linguistic model Role and Reference Grammar (RRG) to analyse and represent the structure and meaning of utterances, via a set of language production and cognition parameters. The model is trained on a Dementia TalkBank dataset with markers of cognitive decline aligned to the global deterioration scale (GDS). A hybrid approach of qualitative linguistic analysis and assessment is applied, which includes the mapping of participants´ tasks of speech utterances and words to RRG phenomena. It uses a metric-based scoring with resulting quantitative scores and qualitative indicators as pre-screening results. This model is to be deployed in a user-centred conversational assessment platform.