BERT for Conversational Question Answering Systems Using Semantic Similarity Estimation

作     者：Abdulaziz Al-Besher Kailash Kumar M.Sangeetha Tinashe Butsa 

作者机构：College of Computing and InformaticsSaudi Electronic UniversityRiyadh11673Kingdom of Saudi Arabia Department of Information TechnologySRMInstitute of Science and TechnologyKattankulathurIndia Department of Information TechnologyHarare Institute of TechnologyBelvedereHarare 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第3期

页      面：4763-4780页

核心收录：

学科分类：0502[文学-外国语言文学] 050201[文学-英语语言文学] 05[文学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Semantic similarity estimation conversational search multi-turn interactions context inference BERT user intent 

摘      要：Most of the questions from users lack the context needed to thoroughly understand the problemat hand,thus making the questions impossible to *** Similarity Estimation is based on relating user’s questions to the context from previous Conversational Search Systems(CSS)to provide answers without requesting the user’s *** imposes constraints on the time needed to produce an answer for the *** proposed model enables the use of contextual data associated with previous Conversational Searches(CS).While receiving a question in a new conversational search,the model determines the question that refers tomore *** then infers past contextual data related to the given question and predicts an answer based on the context inferred without engaging in multi-turn interactions or requesting additional data from the user for *** model shows the ability to use the limited information in user queries for best context inferences based on Closed-Domain-based CS and Bidirectional Encoder Representations from Transformers for textual representations.