Interactive Language Learning by Question Answering

Abstract

Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.

EMNLP 2019

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Noisy Networks for Exploration
• Highway Networks
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Machine Comprehension Using Match-LSTM and Answer Pointer
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Quantifying Generalization in Reinforcement Learning
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Language Understanding for Text-based Games Using Deep Reinforcement Learning
• HoME: a Household Multimodal Environment
• Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
• Blindfold Baselines for Embodied QA
• NAIL: A General Interactive Fiction Agent
• Towards Information-Seeking Agents
• Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System

Cited by in corpus (7)

• Graph Constrained Reinforcement Learning for Natural Language Action Spaces
• Interactive Fiction Games: A Colossal Adventure
• NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks
• Visually Grounded Continual Learning of Compositional Phrases
• NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
• Instance based Generalization in Reinforcement Learning
• Interactive Machine Comprehension with Information Seeking Agents