# Towards Controlled and Diverse Generation of Article Comments

arXiv: https://arxiv.org/abs/2107.11781 · HTML: https://mlsanity.com/paper/2107.11781/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 25 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting](https://mlsanity.com/paper/1805.11080/) (2018)
- [Affect-LM: A Neural Language Model for Customizable Affective Text Generation](https://mlsanity.com/paper/1704.06851/) (2017)
- [Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models](https://mlsanity.com/paper/1701.03185/) (2017)
- [Is Word Segmentation Necessary for Deep Learning of Chinese Representations?](https://mlsanity.com/paper/1905.05526/) (2019)
- [Global Encoding for Abstractive Summarization](https://mlsanity.com/paper/1805.03989/) (2018)
- [Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation](https://mlsanity.com/paper/1712.02250/) (2017)
- [Automatic Article Commenting: the Task and Dataset](https://mlsanity.com/paper/1805.03668/) (2018)
- [Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model](https://mlsanity.com/paper/1906.01231/) (2019)
- [Learning Comment Generation by Leveraging User-Generated Data](https://mlsanity.com/paper/1810.12264/) (2018)
- [Unsupervised Machine Commenting with Neural Variational Topic Model](https://mlsanity.com/paper/1809.04960/) (2018)

## Abstract (arXiv)

Much research in recent years has focused on automatic article commenting. However, few of previous studies focus on the controllable generation of comments. Besides, they tend to generate dull and commonplace comments, which further limits their practical application. In this paper, we make the first step towards controllable generation of comments, by building a system that can explicitly control the emotion of the generated comments. To achieve this, we associate each kind of emotion category with an embedding and adopt a dynamic fusion mechanism to fuse this embedding into the decoder. A sentence-level emotion classifier is further employed to better guide the model to generate comments expressing the desired emotion. To increase the diversity of the generated comments, we propose a hierarchical copy mechanism that allows our model to directly copy words from the input articles. We also propose a restricted beam search (RBS) algorithm to increase intra-sentence diversity. Experimental results show that our model can generate informative and diverse comments that express the desired emotions with high accuracy.