Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
This addresses the challenge of user engagement on online news platforms by improving comment generation, though it is incremental as it builds on existing graph-to-sequence methods for a specific domain.
The paper tackles the problem of generating coherent comments for long Chinese news articles by proposing a graph-to-sequence model that represents articles as topic interaction graphs, resulting in more coherent and informative comments compared to strong baselines.
Automatic article commenting is helpful in encouraging user engagement and interaction on online news platforms. However, the news documents are usually too long for traditional encoder-decoder based models, which often results in general and irrelevant comments. In this paper, we propose to generate comments with a graph-to-sequence model that models the input news as a topic interaction graph. By organizing the article into graph structure, our model can better understand the internal structure of the article and the connection between topics, which makes it better able to understand the story. We collect and release a large scale news-comment corpus from a popular Chinese online news platform Tencent Kuaibao. Extensive experiment results show that our model can generate much more coherent and informative comments compared with several strong baseline models.