Alzheimer's Diagnosis and Generation-Based Chatbot Using Hierarchical Attention and Transformer

In this paper, we propose a natural language processing architecture that can handle tasks that previously required two models as one model.

With a single model, we analyze the language patterns and conversational context of Alzheimer's patients and derive answers from two results: patient classification and chatbot.

If the patient's language characteristics are identified by chatbots in daily life, doctors can plan more precise diagnosis and treatment for early diagnosis.

The proposed model is used to develop chatbots that replace questionnaires that required experts.

There are two natural language processing tasks performed by the model.

The first is a 'natural language classification' that indicates with probability whether the patient has an illness, and the second is to generate the next 'answer' of the chatbot to the patient's answer.

In the first half, a context vector, which is a characteristic of patient utterance, is extracted through a self-attention neural network.

This context vector and chatbot (expert, moderator) questions are entered together into the encoder to obtain a matrix containing the characteristics of the interaction between the questioner and the patient.

The vectorized matrix becomes a probability value for classification of patients.

Enter the matrix into the decoder with the next answer from the chatbot (the moderator) to generate the next utterance.

As a result of learning this structure with DmentiaBank's cookie theft description corpus, it was confirmed that the value of the loss function of the encoder and decoder was significantly reduced and converged.

This shows that capturing the speech language pattern of Alzheimer's disease patients can contribute to early diagnosis and longitudinal studies of the disease in the future.

;Comment: 3 pages, in Korean language, 6 figures, 2022 Journal of The Korea Society of Computer and Information (KSCI)