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

arXiv: https://arxiv.org/abs/1711.03230 · HTML: https://mlsanity.com/paper/1711.03230/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2017.

## Built on by (most cited first, 1 of 1)

- [Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension](https://mlsanity.com/paper/2107.07957/) (2021)

## Abstract (arXiv)

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.