SEE: Semantically Aligned EEG-to-Text Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tao, Yitian, Liang, Yan, Wang, Luoyu, Li, Yongqing, Yang, Qing, Zhang, Han
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909325197312000
author Tao, Yitian
Liang, Yan
Wang, Luoyu
Li, Yongqing
Yang, Qing
Zhang, Han
author_facet Tao, Yitian
Liang, Yan
Wang, Luoyu
Li, Yongqing
Yang, Qing
Zhang, Han
contents Decoding neurophysiological signals into language is of great research interest within brain-computer interface (BCI) applications. Electroencephalography (EEG), known for its non-invasiveness, ease of use, and cost-effectiveness, has been a popular method in this field. However, current EEG-to-Text decoding approaches face challenges due to the huge domain gap between EEG recordings and raw texts, inherent data bias, and small closed vocabularies. In this paper, we propose SEE: Semantically Aligned EEG-to-Text Translation, a novel method aimed at improving EEG-to-Text decoding by seamlessly integrating two modules into a pre-trained BART language model. These two modules include (1) a Cross-Modal Codebook that learns cross-modal representations to enhance feature consolidation and mitigate domain gap, and (2) a Semantic Matching Module that fully utilizes pre-trained text representations to align multi-modal features extracted from EEG-Text pairs while considering noise caused by false negatives, i.e., data from different EEG-Text pairs that have similar semantic meanings. Experimental results on the Zurich Cognitive Language Processing Corpus (ZuCo) demonstrate the effectiveness of SEE, which enhances the feasibility of accurate EEG-to-Text decoding.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16312
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SEE: Semantically Aligned EEG-to-Text Translation
Tao, Yitian
Liang, Yan
Wang, Luoyu
Li, Yongqing
Yang, Qing
Zhang, Han
Quantitative Methods
Artificial Intelligence
Signal Processing
Decoding neurophysiological signals into language is of great research interest within brain-computer interface (BCI) applications. Electroencephalography (EEG), known for its non-invasiveness, ease of use, and cost-effectiveness, has been a popular method in this field. However, current EEG-to-Text decoding approaches face challenges due to the huge domain gap between EEG recordings and raw texts, inherent data bias, and small closed vocabularies. In this paper, we propose SEE: Semantically Aligned EEG-to-Text Translation, a novel method aimed at improving EEG-to-Text decoding by seamlessly integrating two modules into a pre-trained BART language model. These two modules include (1) a Cross-Modal Codebook that learns cross-modal representations to enhance feature consolidation and mitigate domain gap, and (2) a Semantic Matching Module that fully utilizes pre-trained text representations to align multi-modal features extracted from EEG-Text pairs while considering noise caused by false negatives, i.e., data from different EEG-Text pairs that have similar semantic meanings. Experimental results on the Zurich Cognitive Language Processing Corpus (ZuCo) demonstrate the effectiveness of SEE, which enhances the feasibility of accurate EEG-to-Text decoding.
title SEE: Semantically Aligned EEG-to-Text Translation
topic Quantitative Methods
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2409.16312