Adapting Knowledge for Few-shot Table-to-Text Generation
IEEE/ACM Transactions on Audio, Speech, and Language Processing(2023)
Abstract
Pretrained language models (PLMs) have made remarkable progress in
table-to-text generation tasks. However, the lack of domain-specific knowledge
makes it challenging to bridge the topological gap between tabular data and
text, especially in real-world applications with limited resources. To mitigate
the limitation of insufficient labeled data, we propose a novel framework:
Adapt-Knowledge-to-Generate (AKG). The core insight of AKG is to adapt
unlabeled domain-specific knowledge into the model, which brings at least three
benefits: (1) it injects representation of normal table-related descriptions to
bridge the topological gap between tabular data and texts; (2) it enables us to
use large amounts of unlabeled domain-specific knowledge fully, which can
alleviate the PLMs' inherent shortcomings of lacking domain knowledge; (3) it
allows us to design various tasks to employ the domain-specific knowledge.
Extensive experiments and analyses are conducted on three open-domain, few-shot
natural language generation (NLG) data sets: Humans, Songs, and Books. Compared
to previous state-of-the-art approaches, our model achieves superior
performance in terms of both fluency and accuracy as judged by human and
automatic evaluations.
MoreTranslated text
Key words
Few-shot generation,table-to-text generation,knowledge adaption
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined