Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, Jie Ma, Patrick Ng, Zhiguo Wang, Bonan Min, William Yang Wang
Abstract
In this paper, we present a novel approach for data-to-text generation that addresses the limitations of current 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.
BibTeX
@inproceedings{li-etal-2023-shot-data,
title = "Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning",
author = "Li, Alexander Hanbo and
Shang, Mingyue and
Spiliopoulou, Evangelia and
Ma, Jie and
Ng, Patrick and
Wang, Zhiguo and
Min, Bonan and
Wang, William Yang and
McKeown, Kathleen and
Castelli, Vittorio and
Roth, Dan and
Xiang, Bing",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.894/",
doi = "10.18653/v1/2023.acl-long.894",
pages = "16171--16189"
}