Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
This work addresses the challenge of knowledge graph-to-text generation for AI and NLP applications, presenting an incremental improvement with novel technical contributions.
The paper tackles the problem of generating natural language text from knowledge graphs in few-shot settings, achieving state-of-the-art performance on three benchmark datasets by outperforming all comparison methods in both fully-supervised and few-shot scenarios.
This paper studies how to automatically generate a natural language text that describes the facts in knowledge graph (KG). Considering the few-shot setting, we leverage the excellent capacities of pretrained language models (PLMs) in language understanding and generation. We make three major technical contributions, namely representation alignment for bridging the semantic gap between KG encodings and PLMs, relation-biased KG linearization for deriving better input representations, and multi-task learning for learning the correspondence between KG and text. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our model on KG-to-text generation task. In particular, our model outperforms all comparison methods on both fully-supervised and few-shot settings. Our code and datasets are available at https://github.com/RUCAIBox/Few-Shot-KG2Text.