Intelligent Question Answering Model Based on CN-BiLSTM

EasyChair Preprint 130

Abstract

Abstract: An intelligent question-answering system can understand the user's question in the form of natural language and return a concise, accurate answer by searching the knowledge base or corpus. Compared with search engines, intelligent question-answering systems have a better understanding of users' intentions, thereby can meet users’ demand for accuracy information. This paper proposes a novel hybrid model for the contextual query intelligent question-answering task. The model employs convolutional neural network and bidirectional LSTM network to improve the text information encoding capability and capture long-term dependencies of the context. The experiments on bAbi data show that the model is effective and efficient.

Keyphrases: Convolutional Neural Network, Intelligent Question Answering, Natural Language Processing, bidirectional LSTM network

@booklet{EasyChair:130,
  author    = {Chengfei Li and Li Liu and Fan Jiang and Yongzhao Yu},
  title     = {Intelligent Question Answering Model Based on CN-BiLSTM},
  howpublished = {EasyChair Preprint 130},
  year      = {EasyChair, 2018}}