Sketch and Customize: A Counterfactual Story Generator

Authors

  • Changying Hao Institute of Computing Technology, Chinese Academy of Sciences
  • Liang Pang Institute of Computing Technology, Chinese Academy of Sciences
  • Yanyan Lan Institute of Computing Technology, Chinese Academy of Sciences
  • Yan Wang Tencent AI Lab
  • Jiafeng Guo Institute of Computing Technology, Chinese Academy of Sciences
  • Xueqi Cheng Institute of Computing Technology, Chinese Academy of Sciences

Keywords:

Generation

Abstract

Recent text generation models are easy to generate relevant and fluent text for the given text, while lack of causal reasoning ability when we change some parts of the given text. Counterfactual story rewriting is a recently proposed task to test the causal reasoning ability for text generation models, which requires a model to predict the corresponding story ending when the condition is modified to a counterfactual one. Previous works have shown that the traditional sequence-to-sequence model cannot well handle this problem, as it often captures some spurious correlations between the original and counterfactual endings, instead of the causal relations between conditions and endings. To address this issue, we propose a sketch-and-customize generation model guided by the causality implicated in the conditions and endings. In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending. In the customize stage, a generation model is used to fill proper words in the skeleton under the guidance of the counterfactual condition. In this way, the obtained counterfactual ending is both relevant to the original ending and consistent with the counterfactual condition. Experimental results show that the proposed model generates much better endings, as compared with the traditional sequence-to-sequence model.

Downloads

Published

2021-05-18

How to Cite

Hao, C., Pang, L., Lan, Y., Wang, Y., Guo, J., & Cheng, X. (2021). Sketch and Customize: A Counterfactual Story Generator. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12955-12962. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17532

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I