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

TL;DR

This paper introduces SCTKG, a novel essay generation model that incorporates sentiment control and a topic knowledge graph to produce more relevant, diverse, and fluent essays from limited topic words.

Contribution

The paper presents a new CVAE-based model that integrates sentiment control and a structured topic knowledge graph for improved essay generation.

Findings

Outperforms state-of-the-art models in relevance, fluency, and diversity.

Successfully controls sentiment in generated essays.

Utilizes a structured knowledge graph for better semantic coherence.

Abstract

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.