Multi-Head Multi-Layer Attention to Deep Language Representations for Grammatical Error Detection

TL;DR

This paper introduces a multi-head multi-layer attention model that leverages multiple layers of pre-trained language models like BERT to improve grammatical error detection, achieving state-of-the-art results across several datasets.

Contribution

It proposes a novel multi-head multi-layer attention approach to utilize intermediate layers of BERT for grammatical error detection, surpassing existing methods.

Findings

Achieved top scores on three grammatical error detection datasets.

Outperformed previous state-of-the-art by significant margins.

Demonstrated broader information utilization through multi-layer attention.

Abstract

It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary, and simply using the output of the final layer is not necessarily sufficient. Moreover, to our knowledge, exploiting large language representation models to detect grammatical errors has not yet been studied. In this work, we investigate the effect of utilizing information not only from the final layer but also from intermediate layers of a pre-trained language representation model to detect grammatical errors. We propose a multi-head multi-layer attention model that determines the appropriate layers in Bidirectional Encoder Representation from Transformers (BERT). The proposed method achieved the best scores on three datasets for grammatical error detection tasks, outperforming the current state-of-the-art method by 6.0 points on FCE, 8.2 points on CoNLL14, and 12.2 points on JFLEG in terms of F_0.5. We also demonstrate that by using multi-head multi-layer attention, our model can exploit a broader range of information for each token in a sentence than a model that uses only the final layer's information.