Learning Comment Generation by Leveraging User-Generated Data

10/29/2018

∙

by   Zhaojiang Lin, et al.

∙

0

∙

share

Existing models on open-domain comment generation produce repetitive and uninteresting response. To cope with this issue, we propose a combined approach of retrieval and generation methods. We introduce an attentive scorer to retrieve informative and relevant comments by using user-generated data. Then, we use the retrieved comments to train our sequence-to-sequence model with copy mechanism to copy important keywords from articles. We show the robustness of our model, and it can alleviate the issue. In our experiments, our proposed generative model significantly outperforms the Seq2Seq with attention model and Information Retrieval models by around 27 and 30 BLEU-1 points respectively.