Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
This addresses the problem of generating relevant comments for news articles, which is an incremental improvement in natural language generation for media applications.
The authors tackled automatic news comment generation by proposing a 'read-attend-comment' deep architecture with reading and generation networks, and their model significantly outperformed existing methods on two datasets in both automatic and human evaluations.
Automatic news comment generation is a new testbed for techniques of natural language generation. In this paper, we propose a "read-attend-comment" procedure for news comment generation and formalize the procedure with a reading network and a generation network. The reading network comprehends a news article and distills some important points from it, then the generation network creates a comment by attending to the extracted discrete points and the news title. We optimize the model in an end-to-end manner by maximizing a variational lower bound of the true objective using the back-propagation algorithm. Experimental results on two datasets indicate that our model can significantly outperform existing methods in terms of both automatic evaluation and human judgment.