# A Fully Attention-Based Information Retriever

Source: [A Fully Attention-Based Information Retriever](<https://www.sota2.com/research/paper/68fa64f61e209131cea075d6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T02:22:35.206Z

Authors: Alvaro Henrique Chaim Correia, Jorge Luiz Moreira Silva, Thiago de Castro Martins, Fabio Gagliardi Cozman

Published: 2018-10-22T22:10:46.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1810.09580>)

[PDF](<https://arxiv.org/pdf/1810.09580.pdf>)

[Implementation](<https://worksheets.codalab.org/worksheets/0xee647ea284674396831ecb5aae9ca297/>)