Year: 2018
Type: conference-paper
Abstract: We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension.Compared to previous work such as ReasoNet which used reinforcement learning to determine the number of steps, the unique feature is the use of a kind of stochastic prediction dropout on the answer module (final layer) of the neural network during the training.We show that this simple trick improves robustness and achieves results competitive to the state-of-the-art on the Stanford Question Answering Dataset (SQuAD), the Adversarial SQuAD, and the Microsoft MAchine Reading COmprehension Dataset (MS MARCO).
DOI: 10.18653/v1/p18-1157
Authors: Xiaodong Liu, Yelong Shen, Kevin Duh, Jianfeng Gao
Institutions: Microsoft (United States), Johns Hopkins University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2963769536
