Enhancing Text Generation via Multi-Level Knowledge Aware Reasoning

Enhancing Text Generation via Multi-Level Knowledge Aware Reasoning

Feiteng Mu, Wenjie Li

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 4310-4316. https://doi.org/10.24963/ijcai.2022/598

How to generate high-quality textual content is a non-trivial task. Existing methods generally generate text by grounding on word-level knowledge. However, word-level knowledge cannot express multi-word text units, hence existing methods may generate low-quality and unreasonable text. In this paper, we leverage event-level knowledge to enhance text generation. However, event knowledge is very sparse. To solve this problem, we split a coarse-grained event into fine-grained word components to obtain the word-level knowledge among event components. The word-level knowledge models the interaction among event components, which makes it possible to reduce the sparsity of events. Based on the event-level and the word-level knowledge, we devise a multi-level knowledge aware reasoning framework. Specifically, we first utilize event knowledge to make event-based content planning, i.e., select reasonable event sketches conditioned by the input text. Then, we combine the selected event sketches with the word-level knowledge for text generation. We validate our method on two widely used datasets, experimental results demonstrate the effectiveness of our framework to text generation.
Keywords:
Natural Language Processing: Applications
Knowledge Representation and Reasoning: Common-Sense Reasoning
Natural Language Processing: Language Generation