Query-Regression Networks for Machine Comprehension
Minjoon Seo
and
Hannaneh Hajishirzi
and
Ali Farhadi
arXiv e-Print archive - 2016 via Local arXiv
Keywords:
cs.CL, cs.NE
First published: 2016/06/14 (8 years ago) Abstract: We present Query-Regression Network (QRN), a variant of Recurrent Neural
Network (RNN) that is suitable for end-to-end machine comprehension. While
previous work largely relied on external memory and global softmax attention
mechanism, QRN is a single recurrent unit with internal memory and local
sigmoid attention. Unlike most RNN-based models, QRN is able to effectively
handle long-term dependencies and is highly parallelizable. In our experiments
we show that QRN obtains the state-of-the-art result in end-to-end bAbI QA
tasks.
