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

2020/11/16 by Rajkumar Ramamurthy, Rafet Sifa, Ramamurthy, Rajkumar +3
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.2011.08272

Accepted at Wordplay: When Language Meets Games Workshop @ NeurIPS 2020

arxiv created 2020/11/16 · openalex publication_date 2020/11/16 · arxiv updated 2020/11/18 · openalex created_date 2020/11/23 · openalex updated_date 2026/07/28

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

Citations

• Teaching Machines to Read and Comprehend
• Grounded Language Learning in a Simulated 3D World
• R³: Reinforced Reader-Ranker for Open-Domain Question Answering
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning
• Language Understanding for Text-based Games Using Deep Reinforcement\n Learning
• Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• TextWorld: A Learning Environment for Text-based Games
• Interactive Language Learning by Question Answering
• Extractive Summarization as Text Matching

Related

• Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
• Natural Language Reinforcement Learning
• A Survey of Reinforcement Learning Informed by Natural Language
• PARL: Prompt-based Agents for Reinforcement Learning
• NiceWebRL: a Python library for human subject experiments with reinforcement learning environments