NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks

TL;DR

NLPGym is an open-source toolkit that provides simulated textual environments for benchmarking reinforcement learning algorithms on various NLP tasks, enabling consistent evaluation and research advancement.

Contribution

The paper introduces NLPGym, a novel toolkit offering interactive NLP environments for RL, filling a gap in available benchmarking tools for NLP research.

Findings

Experimental results for 6 NLP tasks using different RL algorithms.

NLPGym serves as a baseline for future RL-NLP research.

Toolkit facilitates consistent benchmarking of RL methods in NLP.

Abstract

Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks. To a large extent, this is thanks to the availability of simulated environments such as OpenAI Gym, Atari Learning Environment, or Malmo which allow agents to learn complex tasks through interaction with virtual environments. While RL is also increasingly applied to natural language processing (NLP), there are no simulated textual environments available for researchers to apply and consistently benchmark RL on NLP tasks. With the work reported here, we therefore release NLPGym, an open-source Python toolkit that provides interactive textual environments for standard NLP tasks such as sequence tagging, multi-label classification, and question answering. We also present experimental results for 6 tasks using different RL algorithms which serve as baselines for further research. The toolkit is published at https://github.com/rajcscw/nlp-gym