KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation
Citations Over TimeTop 10% of 2020 papers
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.
Related Papers
- → Self-Training with Selection-by-Rejection(2012)19 cited
- → Automatic Labeling of Tweets for Crisis Response Using Distant Supervision(2020)13 cited
- → The Use of Unlabeled Data Versus Labeled Data for Stopping Active Learning for Text Classification(2019)17 cited
- → A Tri-training Based Transfer Learning Algorithm(2012)3 cited
- → Enhancing Self-Training Methods(2023)