• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于脑电和眼动追踪数据的跨主题阅读任务分类的ZuCo基准测试。

The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data.

作者信息

Hollenstein Nora, Tröndle Marius, Plomecka Martyna, Kiegeland Samuel, Özyurt Yilmazcan, Jäger Lena A, Langer Nicolas

机构信息

Center for Language Technology, University of Copenhagen, Copenhagen, Denmark.

Department of Psychology, University of Zurich, Zurich, Switzerland.

出版信息

Front Psychol. 2023 Jan 12;13:1028824. doi: 10.3389/fpsyg.2022.1028824. eCollection 2022.

DOI:10.3389/fpsyg.2022.1028824
PMID:36710838
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9878684/
Abstract

We present a new machine learning benchmark for reading task classification with the goal of advancing EEG and eye-tracking research at the intersection between computational language processing and cognitive neuroscience. The benchmark task consists of a cross-subject classification to distinguish between two reading paradigms: normal reading and task-specific reading. The data for the benchmark is based on the Zurich Cognitive Language Processing Corpus (ZuCo 2.0), which provides simultaneous eye-tracking and EEG signals from natural reading of English sentences. The training dataset is publicly available, and we present a newly recorded hidden testset. We provide multiple solid baseline methods for this task and discuss future improvements. We release our code and provide an easy-to-use interface to evaluate new approaches with an accompanying public leaderboard: www.zuco-benchmark.com.

摘要

我们提出了一种用于阅读任务分类的新机器学习基准，目标是推动计算语言处理与认知神经科学交叉领域的脑电图（EEG）和眼动追踪研究。该基准任务包括一个跨主体分类，以区分两种阅读范式：正常阅读和特定任务阅读。该基准的数据基于苏黎世认知语言处理语料库（ZuCo 2.0），它提供了来自英语句子自然阅读的同步眼动追踪和EEG信号。训练数据集是公开可用的，并且我们展示了一个新记录的隐藏测试集。我们为该任务提供了多种可靠的基线方法，并讨论了未来的改进方向。我们发布了代码，并提供了一个易于使用的界面，通过随附的公共排行榜（www.zuco-benchmark.com）来评估新方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/6d9a4a5aaa66/fpsyg-13-1028824-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/b500044cd3bb/fpsyg-13-1028824-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/46cfce29e758/fpsyg-13-1028824-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/69b50c21ada3/fpsyg-13-1028824-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/6122766d95cc/fpsyg-13-1028824-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/e47475ebf4b6/fpsyg-13-1028824-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/7af39bbd22d0/fpsyg-13-1028824-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/39ef92d912e5/fpsyg-13-1028824-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/d15c4aa475dd/fpsyg-13-1028824-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/9cf5a7be046c/fpsyg-13-1028824-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/655bea6b1ea2/fpsyg-13-1028824-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/22fcae3387a9/fpsyg-13-1028824-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/6d9a4a5aaa66/fpsyg-13-1028824-g0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/b500044cd3bb/fpsyg-13-1028824-g0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/46cfce29e758/fpsyg-13-1028824-g0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/69b50c21ada3/fpsyg-13-1028824-g0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/6122766d95cc/fpsyg-13-1028824-g0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/e47475ebf4b6/fpsyg-13-1028824-g0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/7af39bbd22d0/fpsyg-13-1028824-g0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/39ef92d912e5/fpsyg-13-1028824-g0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/d15c4aa475dd/fpsyg-13-1028824-g0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/9cf5a7be046c/fpsyg-13-1028824-g0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/655bea6b1ea2/fpsyg-13-1028824-g0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/22fcae3387a9/fpsyg-13-1028824-g0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68f0/9878684/6d9a4a5aaa66/fpsyg-13-1028824-g0012.jpg

相似文献

1
The ZuCo benchmark on cross-subject reading task classification with EEG and eye-tracking data.用于脑电和眼动追踪数据的跨主题阅读任务分类的ZuCo基准测试。
Front Psychol. 2023 Jan 12;13:1028824. doi: 10.3389/fpsyg.2022.1028824. eCollection 2022.
2
ZuCo, a simultaneous EEG and eye-tracking resource for natural sentence reading.ZuCo，一个用于自然句阅读的同时 EEG 和眼动追踪资源。
Sci Data. 2018 Dec 11;5:180291. doi: 10.1038/sdata.2018.291.
3
Neural dynamics of sentiment processing during naturalistic sentence reading.自然阅读句子时情绪处理的神经动力学。
Neuroimage. 2020 Sep;218:116934. doi: 10.1016/j.neuroimage.2020.116934. Epub 2020 May 13.
4
Simultaneous EEG, eye-tracking, behavioral, and screen-capture data during online German language learning.在线德语学习过程中的同步脑电图、眼动追踪、行为和屏幕截图数据。
Data Brief. 2018 Nov 13;21:1937-1943. doi: 10.1016/j.dib.2018.11.044. eCollection 2018 Dec.
5
The Beijing Sentence Corpus: A Chinese sentence corpus with eye movement data and predictability norms.北京句子语料库：具有眼动数据和可预测性规范的中文句子语料库。
Behav Res Methods. 2022 Aug;54(4):1989-2000. doi: 10.3758/s13428-021-01730-2. Epub 2021 Nov 23.
6
Deep Representation Learning for Open Vocabulary Electroencephalography-to-Text Decoding.用于开放词汇脑电图到文本解码的深度表征学习
IEEE J Biomed Health Inform. 2024 Jun 18;PP. doi: 10.1109/JBHI.2024.3416066.
7
CELER: A 365-Participant Corpus of Eye Movements in L1 and L2 English Reading.CELER：一个包含365名参与者的第一语言和第二语言英语阅读眼动语料库。
Open Mind (Camb). 2022 Jul 1;6:41-50. doi: 10.1162/opmi_a_00054. eCollection 2022.
8
Deep Neural Network for EEG Signal-Based Subject-Independent Imaginary Mental Task Classification.用于基于脑电图信号的独立于个体的想象心理任务分类的深度神经网络
Diagnostics (Basel). 2023 Feb 9;13(4):640. doi: 10.3390/diagnostics13040640.
9
Aligning Semantic in Brain and Language: A Curriculum Contrastive Method for Electroencephalography-to-Text Generation.脑与语言的语义对齐：一种用于脑电文本生成的课程对比方法。
IEEE Trans Neural Syst Rehabil Eng. 2023;31:3874-3883. doi: 10.1109/TNSRE.2023.3314642. Epub 2023 Oct 9.
10
Spatiotemporal Eye-Tracking Feature Set for Improved Recognition of Dyslexic Reading Patterns in Children.用于提高儿童阅读障碍识别的时空眼动特征集。
Sensors (Basel). 2022 Jun 29;22(13):4900. doi: 10.3390/s22134900.

引用本文的文献

1
EMTeC: A corpus of eye movements on machine-generated texts.EMTeC：机器生成文本上的眼动语料库。
Behav Res Methods. 2025 Jun 3;57(7):189. doi: 10.3758/s13428-025-02677-4.
2
Comparing human text classification performance and explainability with large language and machine learning models using eye-tracking.使用眼动追踪技术比较大语言和机器学习模型与人类文本分类性能和可解释性。
Sci Rep. 2024 Jun 21;14(1):14295. doi: 10.1038/s41598-024-65080-7.

本文引用的文献

1
The "Narratives" fMRI dataset for evaluating models of naturalistic language comprehension.用于评估自然语言理解模型的“叙事” fMRI 数据集。
Sci Data. 2021 Sep 28;8(1):250. doi: 10.1038/s41597-021-01033-3.
2
Neurophysiological indicators of internal attention: An fMRI-eye-tracking coregistration study.内源性注意的神经生理学指标：一项 fMRI-眼动追踪配准研究。
Cortex. 2021 Oct;143:29-46. doi: 10.1016/j.cortex.2021.07.005. Epub 2021 Jul 19.
3
Decoding EEG Brain Activity for Multi-Modal Natural Language Processing.用于多模态自然语言处理的脑电图脑活动解码
Front Hum Neurosci. 2021 Jul 13;15:659410. doi: 10.3389/fnhum.2021.659410. eCollection 2021.
4
Automated detection of conduct disorder and attention deficit hyperactivity disorder using decomposition and nonlinear techniques with EEG signals.使用 EEG 信号的分解和非线性技术自动检测品行障碍和注意缺陷多动障碍。
Comput Methods Programs Biomed. 2021 Mar;200:105941. doi: 10.1016/j.cmpb.2021.105941. Epub 2021 Jan 14.
5
Brain2Char: a deep architecture for decoding text from brain recordings.脑到字符：一种从脑记录中解码文本的深度架构。
J Neural Eng. 2020 Dec 16;17(6). doi: 10.1088/1741-2552/abc742.
6
Keep it real: rethinking the primacy of experimental control in cognitive neuroscience.保持真实：重新思考认知神经科学中实验控制的首要地位。
Neuroimage. 2020 Nov 15;222:117254. doi: 10.1016/j.neuroimage.2020.117254. Epub 2020 Aug 13.
7
The revolution will not be controlled: natural stimuli in speech neuroscience.这场革命无法被控制：言语神经科学中的自然刺激
Lang Cogn Neurosci. 2018 Jul 22;35(5):573-582. doi: 10.1080/23273798.2018.1499946. eCollection 2020.
8
Neural dynamics of sentiment processing during naturalistic sentence reading.自然阅读句子时情绪处理的神经动力学。
Neuroimage. 2020 Sep;218:116934. doi: 10.1016/j.neuroimage.2020.116934. Epub 2020 May 13.
9
fMRI reveals language-specific predictive coding during naturalistic sentence comprehension.功能磁共振成像揭示了自然语言句子理解过程中的语言特异性预测编码。
Neuropsychologia. 2020 Feb 17;138:107307. doi: 10.1016/j.neuropsychologia.2019.107307. Epub 2019 Dec 24.
10
ZapLine: A simple and effective method to remove power line artifacts.ZapLine：一种简单有效的去除电源线迹的方法。
Neuroimage. 2020 Feb 15;207:116356. doi: 10.1016/j.neuroimage.2019.116356. Epub 2019 Nov 28.