Extracting Action Sequences from Texts Based on Deep Reinforcement Learning
This addresses a challenge in natural language processing for applications like instruction extraction, but it is incremental as it builds on existing reinforcement learning frameworks.
The paper tackles the problem of extracting action sequences from free natural language texts without predefined templates or candidate actions, using deep reinforcement learning to achieve competitive performance on several datasets compared to state-of-the-art methods.
Extracting action sequences from natural language 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 that either the set of candidate actions be provided in advance, or that action descriptions are restricted to a specific form, e.g., description templates. In this paper, we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the candidate 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 the texts associated with actions as "states". We then build Q-networks to learn the policy 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, including online experiments interacting with humans.