[1909.11974] Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
Experimental results on two public data sets indicate that the proposed model can significantly outperform baseline methods in terms of both automatic evaluation and human evaluation.
Abstract: Automatic news comment generation is beneficial for real applications but has
not attracted enough attention from the research community. 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 public
datasets indicate that our model can significantly outperform existing methods
in terms of both automatic evaluation and human judgment.
‹Figure 1: Architecture of our model. The black solid arrows represent differentiable operations and the dashed arrows are non-differentiable operations which represent distilling points from news body. (Approach)Figure 2: The category distribution of Yahoo! News dataset. (Yahoo! News Dataset)
