Convolutional-Match Networks for Question Answering
Abstract
In this paper, we present a simple, yet effective, attention and memory mechanism that is reminiscent 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 convolutional networks; b) distance measurements can be taken at a neuronal level; c) a recursive softmax function can be used for attention; d) extensive weight sharing can help profoundly. We achieve state-of-the-art results in the bAbI tasks, outperforming both Memory Networks and the Differentiable Neural Computer, both in terms of accuracy and stability (i.e. variance) of results.
Cite
Text
Samothrakis et al. "Convolutional-Match Networks for Question Answering." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/374Markdown
[Samothrakis et al. "Convolutional-Match Networks for Question Answering." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/samothrakis2017ijcai-convolutional/) doi:10.24963/IJCAI.2017/374BibTeX
@inproceedings{samothrakis2017ijcai-convolutional,
title = {{Convolutional-Match Networks for Question Answering}},
author = {Samothrakis, Spyridon and Vodopivec, Tom and Fairbank, Michael and Fasli, Maria},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {2686-2692},
doi = {10.24963/IJCAI.2017/374},
url = {https://mlanthology.org/ijcai/2017/samothrakis2017ijcai-convolutional/}
}