An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks

Understand

Reading comprehension (RC) is a challenging task that requires synthesis of information across sentences and multiple turns of reasoning.

• Using a state-of-the-art RC model, we empirically investigate the performance of single-turn and multiple-turn reasoning on the SQuAD and MS MARCO datasets.
• The RC model is an end-to-end neural network with iterative attention, and uses reinforcement learning to dynamically control the number of turns.
• We find that multiple-turn reasoning outperforms single-turn reasoning for all question and answer types; further, we observe that enabling a flexible number of turns generally improves upon a fixed multiple-turn strategy.