Automatic knowledge extraction of any Chatbot from conversation

作者：

Highlights：

• Novel methodology for conversational knowledge extraction from the existing chatbot.

• Building Neural Conversational Agent using a seq2seq-LSTM framework.

• Big noisy dataset is used as a question base to force conversational knowledge extraction.

• K-means clustering algorithm is used to define the stopping point for knowledge extraction.

• Machine-machine conversational knowledge sharing.

摘要

•Novel methodology for conversational knowledge extraction from the existing chatbot.•Building Neural Conversational Agent using a seq2seq-LSTM framework.•Big noisy dataset is used as a question base to force conversational knowledge extraction.•K-means clustering algorithm is used to define the stopping point for knowledge extraction.•Machine-machine conversational knowledge sharing.

论文关键词：Human-machine interaction,Knowledge extraction,Neural conversational agent,Neural network,Rule based chatbot

论文评审过程：Received 30 May 2018, Revised 7 July 2019, Accepted 8 July 2019, Available online 8 July 2019, Version of Record 11 July 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.07.014