English

Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model

Computation and Language 2020-01-24 v1 Machine Learning

Abstract

Consider a natural language sentence describing a specific step in a food recipe. In such instructions, recognizing actions (such as press, bake, etc.) and the resulting changes in the state of the ingredients (shape molded, custard cooked, temperature hot, etc.) is a challenging task. One way to cope with this challenge is to explicitly model a simulator module that applies actions to entities and predicts the resulting outcome (Bosselut et al. 2018). However, such a model can be unnecessarily complex. In this paper, we propose a simplified neural network model that separates action recognition and state change prediction, while coupling the two through a novel loss function. This allows learning to indirectly influence each other. Our model, although simpler, achieves higher state change prediction performance (67% average accuracy for ours vs. 55% in (Bosselut et al. 2018)) and takes fewer samples to train (10K ours vs. 65K+ by (Bosselut et al. 2018)).

Keywords

Cite

@article{arxiv.2001.08665,
  title  = {Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model},
  author = {Qing Wan and Yoonsuck Choe},
  journal= {arXiv preprint arXiv:2001.08665},
  year   = {2020}
}

Comments

AAAI-2020 Student Abstract and Poster Program (Accept)

R2 v1 2026-06-23T13:19:06.239Z