Visualizing attention zones in machine reading comprehension models

Yiming Cui; Wei-Nan Zhang; Ting Liu

doi:10.1016/j.xpro.2022.101481

Visualizing attention zones in machine reading comprehension models

STAR Protoc. 2022 Jun 16;3(3):101481. doi: 10.1016/j.xpro.2022.101481. eCollection 2022 Sep 16.

Authors

Yiming Cui¹, Wei-Nan Zhang², Ting Liu²

Affiliations

¹ Research Center for Social Computing and Information Retrieval (SCIR), Harbin Institute of Technology, Harbin 150001, China; State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, Beijing 100083, China. Electronic address: ymcui@ir.hit.edu.cn.
² Research Center for Social Computing and Information Retrieval (SCIR), Harbin Institute of Technology, Harbin 150001, China.

Abstract

The attention mechanism plays an important role in the machine reading comprehension (MRC) model. Here, we describe a pipeline for building an MRC model with a pretrained language model and visualizing the effect of each attention zone in different layers, which can indicate the explainability of the model. With the presented protocol and accompanying code, researchers can easily visualize the relevance of each attention zone in the MRC model. This approach can be generalized to other pretrained language models. For complete details on the use and execution of this protocol, please refer to Cui et al. (2022).

Keywords: Bioinformatics; Cognitive Neuroscience; Computer sciences; Systems biology.

MeSH terms

Comprehension*
Language*