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

By Peng Wang, Junyang Lin, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang. 2021

25 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Weizhu Chen
  2. Nan Duan
  3. Yelong Shen
  4. Jianfeng Gao
  5. Zhihong Shao
  6. Zhibin Gou
  7. Yeyun Gong
  8. Yujiu Yang

Citations in the corpus