A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment
This work addresses a domain-specific problem for elders with cognitive impairment by providing a dataset and method to enhance dialogue systems, though it is incremental as it builds on existing cognitive dialogue approaches.
The paper tackles data sparsity in Chinese cognitive stimulation dialogue systems for elders with cognitive impairment by constructing a dataset (CSConv) with 2.6K dialogue groups and proposing a multi-source knowledge fusion method to generate responses guided by cognitive stimulation principles and emotional support strategies, showing effectiveness in experiments but with room for improvement compared to human performance.
When communicating with elders with cognitive impairment, cognitive stimulation (CS) help to maintain the cognitive health of elders. Data sparsity is the main challenge in building CS-based dialogue systems, particularly in the Chinese language. To fill this gap, we construct a Chinese CS conversation (CSConv) dataset, which contains about 2.6K groups of dialogues with CS principles and emotional support strategy labels. Making chit chat while providing emotional support is overlooked by the majority of existing cognitive dialogue systems. In this paper, we propose a multi-source knowledge fusion method for CS dialogue (CSD), to generate open-ended responses guided by the CS principle and emotional support strategy. We first use a progressive mask method based on external knowledge to learn encoders as effective classifiers, which is the prerequisite to predict the CS principle and emotional support strategy of the target response. Then a decoder interacts with the perceived CS principle and emotional support strategy to generate responses. Extensive experiments conducted on the CSConv dataset demonstrate the effectiveness of the proposed method, while there is still a large space for improvement compared to human performance.