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

Yelong Shen, Xiaodong Liu, Kevin Duh, Jianfeng Gao


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.
Anthology ID:
I17-1096
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
957–966
Language:
URL:
https://aclanthology.org/I17-1096
DOI:
Bibkey:
Cite (ACL):
Yelong Shen, Xiaodong Liu, Kevin Duh, and Jianfeng Gao. 2017. An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 957–966, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks (Shen et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/I17-1096.pdf
Data
MS MARCOSQuAD