Published as a conference paper at ICLR 2018 S IMULATING A CTION D YNAMICS WITH N EURAL P ROCESS N ETWORKS

Understanding procedural language requires anticipating the causal effects of actions, even when they are not explicitly stated. In this work, we introduce Neural Process Networks to understand procedural text through (neural) simulation of action dynamics. Our model complements existing memory architectures with dynamic entity tracking by explicitly modeling actions as state transformers. The model updates the states of the entities by executing learned action operators. Empirical results demonstrate that our proposed model can reason about the unstated causal effects of actions, allowing it to provide more accurate contextual information for understanding and generating procedural text, all while offering more interpretable internal representations than existing alternatives.

[1]  Benjamin Z. Yao,et al.  Unsupervised learning of event AND-OR grammar and semantics from video , 2011, 2011 International Conference on Computer Vision.

[2]  Yoko Yamakata,et al.  A Machine Learning Approach to Recipe Text Processing , 2012 .

[3]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[4]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[5]  Yamakata Yoko,et al.  Flow Graph Corpus from Recipe Texts , 2013 .

[6]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[7]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[8]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[9]  Thomas B. Schön,et al.  From Pixels to Torques: Policy Learning with Deep Dynamical Models , 2015, ICML 2015.

[10]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[11]  Omer Levy,et al.  Do Supervised Distributional Methods Really Learn Lexical Inference Relations? , 2015, NAACL.

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Yejin Choi,et al.  Mise en Place: Unsupervised Interpretation of Instructional Recipes , 2015, EMNLP.

[14]  Honglak Lee,et al.  Action-Conditional Video Prediction using Deep Networks in Atari Games , 2015, NIPS.

[15]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[16]  Yang Liu,et al.  Modeling Coverage for Neural Machine Translation , 2016, ACL.

[17]  Jason Weston,et al.  The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations , 2015, ICLR.

[18]  Yejin Choi,et al.  Globally Coherent Text Generation with Neural Checklist Models , 2016, EMNLP.

[19]  Shaohua Yang,et al.  Physical Causality of Action Verbs in Grounded Language Understanding , 2016, ACL.

[20]  Song-Chun Zhu,et al.  Jointly Learning Grounded Task Structures from Language Instruction and Visual Demonstration , 2016, EMNLP.

[21]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[22]  Quoc V. Le,et al.  Neural Programmer: Inducing Latent Programs with Gradient Descent , 2015, ICLR.

[23]  Jason Weston,et al.  Tracking the World State with Recurrent Entity Networks , 2016, ICLR.

[24]  Wang Ling,et al.  Reference-Aware Language Models , 2016, EMNLP.

[25]  Jon Gauthier,et al.  Are Distributional Representations Ready for the Real World? Evaluating Word Vectors for Grounded Perceptual Meaning , 2017, RoboNLP@ACL.

[26]  Ali Farhadi,et al.  Query-Reduction Networks for Question Answering , 2016, ICLR.

[27]  Yejin Choi,et al.  Dynamic Entity Representations in Neural Language Models , 2017, EMNLP.

[28]  Martín Abadi,et al.  Learning a Natural Language Interface with Neural Programmer , 2016, ICLR.

[29]  Percy Liang,et al.  Adversarial Examples for Evaluating Reading Comprehension Systems , 2017, EMNLP.