Beyond current conversational chatbots or task-oriented dialogue systems that have attracted increasing attention, we move forward to develop a dialogue system for automatic medical diagnosis that converses with patients to collect additional symptoms beyond their self-reports and automatically makes a diagnosis. Besides the challenges for conversational dialogue systems (e.g. topic transition coherency and question understanding), automatic medical diagnosis further poses more critical requirements for the dialogue rationality in the context of medical knowledge and symptom-disease relations. Existing dialogue systems (Madotto, Wu, and Fung 2018;Wei et al. 2018;Li et al. 2017) mostly rely on datadriven learning and cannot be able to encode extra expert knowledge graph. In this work, we propose an End-to-End Knowledge-routed Relational Dialogue System (KR-DS) that seamlessly incorporates rich medical knowledge graph into the topic transition in dialogue management, and makes it cooperative with natural language understanding and natural language generation. A novel Knowledge-routed Deep Q-network (KR-DQN) is introduced to manage topic transitions, which integrates a relational refinement branch for encoding relations among different symptoms and symptomdisease pairs, and a knowledge-routed graph branch for topic decision-making. Extensive experiments on a public medical dialogue dataset show our KR-DS significantly beats stateof-the-art methods (by more than 8% in diagnosis accuracy). We further show the superiority of our KR-DS on a newly collected medical dialogue system dataset, which is more challenging retaining original self-reports and conversational data between patients and doctors.
a b s t r a c tForecasting the export and import volume in international trade is the prerequisite of a government's policy-making and guidance for a healthier international trade development. However, an individual forecast may not always perform satisfactorily, while combination of forecasts may result in a better forecast than component forecasts. We believe the component forecasts employed in combined forecasts are a description of the actual time series, which is fuzzy. This paper attempts to use forecasting accuracy as the criterion of fuzzy membership function, and proposes a combined forecasting approach based on fuzzy soft sets. This paper also examines the method with data of international trade from 1993 to 2006 in the Chongqing Municipality of China and compares it with a combined forecasting approach based on rough sets and each individual forecast. The experimental results show that the combined approach provided in this paper improves the forecasting performance of each individual forecast and is free from a rough sets approach's restrictions as well. It is a promising forecasting approach and a new application of soft sets theory.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.