Few-Shot Table-to-Text Generation with Prototype Memory

TL;DR

This paper introduces the Prototype-to-Generate framework that enhances few-shot table-to-text generation by leveraging retrieved prototypes, significantly improving performance with limited training data.

Contribution

The paper proposes a novel Prototype-to-Generate framework that effectively uses prototypes to bridge structural gaps in few-shot table-to-text generation tasks.

Findings

Significant performance improvements on three benchmark datasets.

Effective use of prototypes with an IR system and selector.

Compatibility with multiple state-of-the-art models.

Abstract

Neural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in real-world applications. To address this, we propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector to help the model bridging the structural gap between tables and texts. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics.