Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation

Abstract

Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from low coverage and poor faithfulness problems. To mitigate these problems, we propose a novel Skeleton-based two-stage method that combines both Autoregressive and Non-Autoregressive generations (SANA). Our approach includes: (1) skeleton generation with an autoregressive pointer network to select key tokens from the source table; (2) edit-based non-autoregressive generation model to produce texts via iterative insertion and deletion operations. By integrating hard constraints from the skeleton, the non-autoregressive model improves the generation's coverage over the source table and thus enhances its faithfulness. We conduct automatic and human evaluations on both WikiPerson and WikiBio datasets. Experimental results demonstrate that our method outperforms the previous state-of-the-art methods in both automatic and human evaluation, especially on coverage and faithfulness. In particular, we achieve PARENT-T recall of 99.47 in WikiPerson, improving over the existing best results by more than 10 points.

arXiv comment13 pages, 2 figures. Accepted in ACL2021 Findings

References in corpus (9)

• Levenshtein Transformer
• fairseq: A Fast, Extensible Toolkit for Sequence Modeling
• Challenges in Data-to-Document Generation
• Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
• Describing a Knowledge Base
• On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
• Lexically Constrained Neural Machine Translation with Levenshtein Transformer
• Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
• Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation