Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation

TL;DR

This paper introduces a deep neural architecture that reads news articles, identifies key points, and generates relevant comments, advancing automatic news comment generation techniques.

Contribution

It proposes a novel read-attend-comment framework with an end-to-end training method for improved comment generation.

Findings

Model outperforms existing methods in automatic evaluation.

Model achieves higher human judgment scores.

Effective comprehension and comment generation on news articles.

Abstract

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.