Identifying Facts for Chatbot's Question Answering via Sequence labelling Using Recurrent Neural Networks
Question answering(QA)is one of the most significant tasks in artificial intelligence(AI)that not yet solved completely.It is a task which requires building data models capable of providing answers to questions expressed in human language.Full question answering involves some form of labelling.Sequence labelling is an important problem in natural language processing.Given a sequence of words,sequence tagging aims to predict a linguistic tag for each word such as the POS tag.The main question is,how can we leverage the sequential nature of data to extract better features and structural dependency between them.In an effort to address this question,this study present attention-based architecture for sequence labelling on deep recurrent neural network(DRNN).To solve the QA problem,it consists of two major steps:identifying the fact and answering the question based on the relevant fact.The study showed that the proposed model provides consistent improvement and outperform then traditional approaches.
Recurrent Neural Networks Deep Learning Sequence Labelling AI Chatbot Deep Neural Networks
Mohammad Nuruzzaman Omar Khadeer Hussain
School of Business University of New South Wales Canberra,ACT,Australia
国际会议
2019国图灵大会(ACM Turing Celebration conference-China 2019 )
成都
英文
181-187
2019-05-17（万方平台首次上网日期，不代表论文的发表时间）