Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models

TL;DR

This paper presents a novel approach for few-shot knowledge graph-to-text generation using pretrained language models, introducing techniques like representation alignment, relation-biased linearization, and multi-task learning, achieving superior results on benchmark datasets.

Contribution

The paper introduces a new method combining representation alignment, relation-biased linearization, and multi-task learning for improved few-shot KG-to-text generation with pretrained models.

Findings

Outperforms existing methods on benchmark datasets.

Effective in both fully-supervised and few-shot settings.

Demonstrates the benefit of multi-task learning for KG-to-text tasks.

Abstract

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.