A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment

TL;DR

This paper introduces a Chinese cognitive stimulation dialogue system for elders with cognitive impairment, utilizing multi-source knowledge fusion to generate emotionally supportive responses, addressing data sparsity and language-specific challenges.

Contribution

It constructs a new Chinese CS conversation dataset and proposes a multi-source knowledge fusion method for more effective, emotionally supportive dialogue generation.

Findings

The dataset contains 2.6K dialogue groups with CS principles and emotional support labels.

The proposed method outperforms baseline models in response quality.

There is still significant room for improvement compared to human responses.

Abstract

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.