Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning

TL;DR

This paper introduces a unified data representation and multi-source learning approach for structured data-to-text generation, significantly improving adaptability and performance across various data formats and few-shot scenarios.

Contribution

It proposes a novel unified representation enabling multi-task training and zero-shot learning for diverse structured data types, advancing the generality of data-to-text systems.

Findings

66% improvement in zero-shot BLEU scores on knowledge graph data

Effective adaptation to new structured data forms

Enhanced performance over existing methods

Abstract

We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios by providing a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. We demonstrate that our proposed approach can effectively adapt to new structured forms, and can improve performance in comparison to current methods. For example, our method resulted in a 66% improvement in zero-shot BLEU scores when transferring models trained on table inputs to a knowledge graph dataset. Our proposed method is an important step towards a more general data-to-text generation framework.