Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
This addresses the need for more general data-to-text generation frameworks, though it appears incremental by building on existing methods.
The paper tackles the problem of structured data-to-text generation by proposing a unified representation to handle various data forms like tables and knowledge graphs, resulting in a 66% improvement in zero-shot BLEU scores when transferring models from table inputs to a knowledge graph dataset.
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.