Interactive Language Learning by Question Answering
This addresses a problem for machine reading systems by moving beyond static tasks to interactive comprehension, though it is incremental as it builds on existing QA frameworks with new dynamics.
The authors tackled the lack of interactive, information-seeking components in machine reading comprehension by introducing QAit, a novel text-based question answering task where agents interact with partially observable environments to gather information, and experiments showed it poses a major challenge for existing systems while humans solve it easily.
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.