A Fully Attention-Based Information Retriever
Abstract
Recurrent neural networks are now the state-of-the-art in natural language processing because they can build rich contextual representations and process texts of arbitrary length. However, recent developments on attention mechanisms have equipped feedforward networks with similar capabilities, hence enabling faster computations due to the increase in the number of operations that can be parallelized. We explore this new type of architecture in the domain of question-answering and propose a novel approach that we call Fully Attention Based Information Retriever (FABIR). We show that FABIR achieves competitive results in the Stanford Question Answering Dataset (SQuAD) while having fewer parameters and being faster at both learning and inference than rival methods.
Cite
@article{arxiv.1810.09580,
title = {A Fully Attention-Based Information Retriever},
author = {Alvaro Henrique Chaim Correia and Jorge Luiz Moreira Silva and Thiago de Castro Martins and Fabio Gagliardi Cozman},
journal= {arXiv preprint arXiv:1810.09580},
year = {2018}
}
Comments
Accepted for presentation at the International Joint Conference on Neural Networks (IJCNN) 2018