Topic-to-Essay Generation with Comprehensive Knowledge Enhancement

TL;DR

This paper introduces TEGKE, a novel model for topic-to-essay generation that leverages comprehensive internal and external knowledge sources, including a teacher-student framework and a knowledge graph encoder, to produce high-quality, diverse essays.

Contribution

The paper proposes TEGKE, a new approach combining internal knowledge transfer and an advanced external knowledge graph encoder with adversarial training for improved essay generation.

Findings

Achieves state-of-the-art performance in automatic evaluations.

Outperforms baselines in human assessments.

Effectively utilizes knowledge graphs for better content quality.

Abstract

Generating high-quality and diverse essays with a set of topics is a challenging task in natural language generation. Since several given topics only provide limited source information, utilizing various topic-related knowledge is essential for improving essay generation performance. However, previous works cannot sufficiently use that knowledge to facilitate the generation procedure. This paper aims to improve essay generation by extracting information from both internal and external knowledge. Thus, a topic-to-essay generation model with comprehensive knowledge enhancement, named TEGKE, is proposed. For internal knowledge enhancement, both topics and related essays are fed to a teacher network as source information. Then, informative features would be obtained from the teacher network and transferred to a student network which only takes topics as input but provides comparable information compared with the teacher network. For external knowledge enhancement, a topic knowledge graph encoder is proposed. Unlike the previous works only using the nearest neighbors of topics in the commonsense base, our topic knowledge graph encoder could exploit more structural and semantic information of the commonsense knowledge graph to facilitate essay generation. Moreover, the adversarial training based on the Wasserstein distance is proposed to improve generation quality. Experimental results demonstrate that TEGKE could achieve state-of-the-art performance on both automatic and human evaluation.