English

Be Consistent! Improving Procedural Text Comprehension using Label Consistency

Computation and Language 2019-06-24 v1 Machine Learning

Abstract

Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe). This task is challenging as the world is changing throughout the text, and despite recent advances, current systems still struggle with this task. Our approach is to leverage the fact that, for many procedural texts, multiple independent descriptions are readily available, and that predictions from them should be consistent (label consistency). We present a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model. Evaluation on a standard benchmark dataset for procedural text, ProPara (Dalvi et al., 2018), shows that our approach significantly improves prediction performance (F1) over prior state-of-the-art systems.

Keywords

Cite

@article{arxiv.1906.08942,
  title  = {Be Consistent! Improving Procedural Text Comprehension using Label Consistency},
  author = {Xinya Du and Bhavana Dalvi Mishra and Niket Tandon and Antoine Bosselut and Wen-tau Yih and Peter Clark and Claire Cardie},
  journal= {arXiv preprint arXiv:1906.08942},
  year   = {2019}
}

Comments

NAACL 2019

R2 v1 2026-06-23T09:59:36.147Z