Towards a Better Understanding of Human Reading Comprehension with Brain Signals
Ziyi Ye1, Xiaohui Xie1, Yiqun Liu∗1{}^{1}*, Zhihong Wang1, Xuesong Chen1, Min Zhang1, and Shaoping Ma1 1Department of Computer Science and Technology, Institute for Artificial Intelligence, Beijing National Research Center for Information Science and Technology, Tsinghua University Beijing China
Abstract
Reading comprehension is a complex cognitive process involving many human brain activities. However, little is known about what happens in human brain during reading comprehension and how these cognitive activities can affect information retrieval process. Additionally, with the advances in brain imaging techniques such as electroencephalogram (EEG), it is possible to collect brain signals in almost real time and explore whether it can be utilized as feedback to facilitate information acquisition performance.
中文速览
人类阅读理解时大脑究竟发生了什么，这些神经活动能否反过来帮助信息检索系统——这正是本文要回答的核心问题。研究者招募21名大学生，让他们在佩戴脑电图（EEG）设备的情况下完成问答式阅读任务，通过事件相关电位（ERP）分析发现：当读者遇到答案词、语义相关词和普通词时，大脑的神经反应存在显著差异，具体表现为与认知负荷相关的N100-P200成分的幅度变化，以及答案词引发的更强P600成分（与推理加工有关）。基于这些神经机制，研究者设计了一套统一的EEG阅读理解建模框架（UERCM），将脑电信号作为隐式反馈用于两项任务：答案句分类和答案词定位，实验结果分别在MAP和AUC指标上取得了约0.18和0.16的显著提升。这项工作首次系统揭示了信息检索场景下阅读理解的认知神经基础，并证明了将便携式脑机接口引入主动式人机交互系统的实际可行性。
原文 arXiv:2108.01360;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2108.01360v3