IntelliBot: A Dialogue-based chatbot for the insurance industry

作者：

Highlights：

• Proposes IntelliBot, which is a domain-specific chatbot for the insurance sector.

• Response generation is multi-strategy reliant on template-based, knowledge-based, internet retrieval and generative-based strategies.

• In generative-based strategy, proposes a seq2seq model with attention mechanism in Recurrent Neural Networks (RNN).

• Compares the results of IntelliBot and demonstrates its superiority with three existing chatbots in the insurance domain.

摘要

•Proposes IntelliBot, which is a domain-specific chatbot for the insurance sector.•Response generation is multi-strategy reliant on template-based, knowledge-based, internet retrieval and generative-based strategies.•In generative-based strategy, proposes a seq2seq model with attention mechanism in Recurrent Neural Networks (RNN).•Compares the results of IntelliBot and demonstrates its superiority with three existing chatbots in the insurance domain.

论文关键词：Chatbot,Dialogue-based System,Deep neural networks,Recurrent Neural Networks,Deep Learning,Seq2Seq Model

论文评审过程：Received 18 September 2019, Revised 21 March 2020, Accepted 22 March 2020, Available online 26 March 2020, Version of Record 16 April 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105810