English

Incorporating Task-specific Concept Knowledge into Script Learning

Computation and Language 2023-04-25 v3 Machine Learning

Abstract

In this paper, we present Tetris, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance. The dataset, repository, and models will be publicly available to facilitate further research on this new task.

Cite

@article{arxiv.2209.00068,
  title  = {Incorporating Task-specific Concept Knowledge into Script Learning},
  author = {Chenkai Sun and Tie Xu and ChengXiang Zhai and Heng Ji},
  journal= {arXiv preprint arXiv:2209.00068},
  year   = {2023}
}
R2 v1 2026-06-28T00:30:57.973Z