Year: 2022
Type: preprint
Abstract: Question classification is one of the important links in the research of question and answering system. The existing question classification models are more trained on public data sets. At present, there is a lack of question classification data sets in specific fields, especially in the medical field. To make up for this gap, this paper presents a data set for question classification in the medical field. Moreover, this paper proposes a multi-dimensional extraction of the characteristics of the question by combining multiple neural network models, and proposes a question classification model based on multi-dimensional feature extraction. The experimental results show that the proposed method can effectively improve the performance of question classification.
Source: arXiv (Cornell University)
Author: Liu, Jinzhang
Institution: Chinese University of Hong Kong
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4226468065