An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
arXiv:1711.03230
Abstract
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. %across all question types, and is particularly beneficial to questions with lengthy, descriptive answers. We achieve results competitive to the state-of-the-art on these two datasets.
References in corpus (9)
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Differentiable Learning of Logical Rules for Knowledge Base Reasoning
- Learning Recurrent Span Representations for Extractive Question Answering
- Multi-Perspective Context Matching for Machine Comprehension
- Making Neural QA as Simple as Possible but not Simpler
- Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
- Separating Answers from Queries for Neural Reading Comprehension