# Lightweight Convolutional Approaches to Reading Comprehension on SQuAD

Source: [Lightweight Convolutional Approaches to Reading Comprehension on SQuAD](<https://www.sota2.com/research/paper/68fa64f51e209131cea07516>)

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

Data updated: 2025-10-28T13:56:37.115Z

Authors: Tobin Bell, Benjamin Penchas

Published: 2018-10-19T20:32:36.000Z

## Abstract

Current state-of-the-art reading comprehension models rely heavily on recurrent neural networks. We explored an entirely different approach to question answering: a convolutional model. By their nature, these convolutional models are fast to train and capture local dependencies well, though they can struggle with longer-range dependencies and thus require augmentation to achieve comparable performance to RNN-based models. We conducted over two dozen controlled experiments with convolutional models and various kernel/attention/regularization schemes to determine the precise performance gains of each strategy, while maintaining a focus on speed. We ultimately ensembled three models: crossconv (0.5398 dev F1), attnconv (0.5665), and maybeconv (0.5285). The ensembled model was able to achieve a 0.6238 F1 score using the official SQuAD evaluation script. Our individual convolutional model crossconv was able to exceed the performance of the RNN-plus-attention baseline by 25% while training 6 times faster.

## 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/1810.08680>)

[PDF](<https://arxiv.org/pdf/1810.08680.pdf>)
