NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification
Read the original on arXiv Computation and Language →NarraSpace is a multimodal framework that links words and speech times to specific picture elements in picture‑description dementia classification tasks. It retrieves utterances for predefined scene events, summarizes coverage and temporal organization, and uses a frozen language model to contrast event text between Alzheimer’s disease and healthy controls, incorporating transcript surprisal and coverage metrics. On the Alzheimer’s Dementia Recognition through Spontaneous Speech benchmark, a support vector classifier built on these features achieves about 81% accuracy and 91% AUC, while the system preserves source records that map event scores back to utterances, speech intervals, and lexical matches.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.