# A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph

arXiv: https://arxiv.org/abs/2010.05511 · HTML: https://mlsanity.com/paper/2010.05511/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation](https://mlsanity.com/paper/2209.10797/) (2022)
- [Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring](https://mlsanity.com/paper/2106.06719/) (2021)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [A Survey of Natural Language Generation](https://mlsanity.com/paper/2112.11739/) (2021)
- [SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach](https://mlsanity.com/paper/2204.12184/) (2022)
- [Topic-to-Essay Generation with Comprehensive Knowledge Enhancement](https://mlsanity.com/paper/2106.15142/) (2021)
- [TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence](https://mlsanity.com/paper/2212.13456/) (2022)
- [Topic-to-essay generation with knowledge-based content selection](https://mlsanity.com/paper/2402.16248/) (2024)

## Abstract (arXiv)

Generating a vivid, novel, and diverse essay with only several given topic words is a challenging task of natural language generation. In previous work, there are two problems left unsolved: neglect of sentiment beneath the text and insufficient utilization of topic-related knowledge. Therefore, we propose a novel Sentiment-Controllable topic-to-essay generator with a Topic Knowledge Graph enhanced decoder, named SCTKG, which is based on the conditional variational autoencoder (CVAE) framework. We firstly inject the sentiment information into the generator for controlling sentiment for each sentence, which leads to various generated essays. Then we design a Topic Knowledge Graph enhanced decoder. Unlike existing models that use knowledge entities separately, our model treats the knowledge graph as a whole and encodes more structured, connected semantic information in the graph to generate a more relevant essay. Experimental results show that our SCTKG can generate sentiment controllable essays and outperform the state-of-the-art approach in terms of topic relevance, fluency, and diversity on both automatic and human evaluation.