Few-Shot Table-to-Text Generation with Prefix-Controlled Generator
This addresses the challenge of generating accurate and fluent text from tables for real-world applications with limited data, though it is incremental as it builds on existing pre-trained language models.
The paper tackles the problem of neural table-to-text generation being data-hungry and prone to hallucinations in low-resource settings, proposing a prompt-based approach that improves performance on the Wikibio dataset across domains like humans, books, and songs.
Neural table-to-text generation approaches are data-hungry, limiting their adaptation for low-resource real-world applications. Previous works mostly resort to Pre-trained Language Models (PLMs) to generate fluent summaries of a table. However, they often contain hallucinated contents due to the uncontrolled nature of PLMs. Moreover, the topological differences between tables and sequences are rarely studied. Last but not least, fine-tuning on PLMs with a handful of instances may lead to over-fitting and catastrophic forgetting. To alleviate these problems, we propose a prompt-based approach, Prefix-Controlled Generator (i.e., PCG), for few-shot table-to-text generation. We prepend a task-specific prefix for a PLM to make the table structure better fit the pre-trained input. In addition, we generate an input-specific prefix to control the factual contents and word order of the generated text. Both automatic and human evaluations on different domains (humans, books and songs) of the Wikibio dataset show substantial improvements over baseline approaches.