Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
arXiv:1906.01231
Abstract
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.
Accepted by ACL 2019
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Graph Convolutional Matrix Completion
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Get To The Point: Summarization with Pointer-Generator Networks
- Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
- Graph Convolutional Networks for Text Classification
- Multiresolution Graph Attention Networks for Relevance Matching
- A Graph-to-Sequence Model for AMR-to-Text Generation
- Automatic Article Commenting: the Task and Dataset
- Unsupervised Machine Commenting with Neural Variational Topic Model
- SQL-to-Text Generation with Graph-to-Sequence Model
- Learning Comment Generation by Leveraging User-Generated Data
Cited by in corpus (5)
- A Survey of Knowledge-Enhanced Text Generation
- EQG-RACE: Examination-Type Question Generation
- HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network
- Towards Controlled and Diverse Generation of Article Comments
- DCA: Diversified Co-Attention towards Informative Live Video Commenting