Extracting Action Sequences from Texts Based on Deep Reinforcement Learning

Extracting Action Sequences from Texts Based on Deep Reinforcement Learning

Wenfeng Feng, Hankz Hankui Zhuo, Subbarao Kambhampati

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 4064-4070. https://doi.org/10.24963/ijcai.2018/565

Extracting action sequences from texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require either the set of candidate actions be provided in advance, or action descriptions are restricted to a specific form, e.g., description templates. In this paper we aim to extract action sequences from texts in \emph{free} natural language, i.e., without any restricted templates, provided the set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view ``selecting'' or ``eliminating'' words from texts as ``actions'', and texts associated with actions as ``states''. We build Q-networks to learn policies of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches.
Keywords:
Natural Language Processing: Natural Language Processing
Planning and Scheduling: Activity and Plan Recognition
Planning and Scheduling: Planning with Incomplete information
Machine Learning: Deep Learning