KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

TL;DR

KGPT introduces a knowledge-grounded pre-training approach for data-to-text generation, enabling effective transfer learning across tasks and domains with minimal labeled data, achieving state-of-the-art results especially in zero-shot and few-shot scenarios.

Contribution

The paper presents a novel pre-training paradigm leveraging web-crawled knowledge-grounded text to improve data-to-text generation, especially in low-resource settings.

Findings

Achieves over 30 ROUGE-L in zero-shot WebNLG

Requires only one-fifteenth of labeled data in few-shot settings

Demonstrates strong generalization across tasks and domains

Abstract

Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However, they rely on a significant amount of labeled data for each task, which is costly to acquire and thus limits their application to new tasks and domains. In this paper, we propose to leverage pre-training and transfer learning to address this issue. We propose a knowledge-grounded pre-training (KGPT), which consists of two parts, 1) a general knowledge-grounded generation model to generate knowledge-enriched text. 2) a pre-training paradigm on a massive knowledge-grounded text corpus crawled from the web. The pre-trained model can be fine-tuned on various data-to-text generation tasks to generate task-specific text. We adopt three settings, namely fully-supervised, zero-shot, few-shot to evaluate its effectiveness. Under the fully-supervised setting, our model can achieve remarkable gains over the known baselines. Under zero-shot setting, our model without seeing any examples achieves over 30 ROUGE-L on WebNLG while all other baselines fail. Under the few-shot setting, our model only needs about one-fifteenth as many labeled examples to achieve the same level of performance as baseline models. These experiments consistently prove the strong generalization ability of our proposed framework https://github.com/wenhuchen/KGPT.