Research Repository

Convolutional-Match Networks for Question Answering

Samothrakis, S and Vodopivec, T and Fairbank, M and Fasli, M (2017) Convolutional-Match Networks for Question Answering. In: International Joint Conference on Artificial Intelligence (IJCAI), 2017-08-19 - 2017-08-25, Melbourne.


Download (154kB) | Preview


In this paper, we present a simple, yet effective, attention and memory mechanism that is reminis- cent of Memory Networks and we demonstrate it in question-answering scenarios. Our mechanism is based on four simple premises: a) memories can be formed from word sequences by using convo- lutional networks; b) distance measurements can be taken at a neuronal level; c) a recursive soft- max function can be used for attention; d) extensive weight sharing can help profoundly. We achieve state-of-the-art results in the bAbI tasks, outper- forming Memory Networks and the Differentiable Neural Computer, both in terms of accuracy and stability (i.e. variance) of results.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Uncontrolled Keywords: Machine Learning: Neural Networks; Machine Learning: Deep Learning
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 29 Sep 2017 13:03
Last Modified: 23 Sep 2022 19:19

Actions (login required)

View Item View Item