Incorporating knowledge into neural network for text representation

作者：

Highlights：

• A framework which incorporates knowledge into neural network is proposed.

• The framework is a kind of architecture to produce knowledge based text features.

• A method for transforming a raw text into a conceptualized text is proposed.

• The framework is tested on the sentence level task and the document level task.

摘要

•A framework which incorporates knowledge into neural network is proposed.•The framework is a kind of architecture to produce knowledge based text features.•A method for transforming a raw text into a conceptualized text is proposed.•The framework is tested on the sentence level task and the document level task.

论文关键词：Text representation,Knowledge base,Representation learning,Network embedding

论文评审过程：Received 4 July 2017, Revised 14 November 2017, Accepted 15 November 2017, Available online 22 November 2017, Version of Record 22 December 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.037