Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for EEG2Text have neglected EEG instability, a problem that has confounded inference and sparked debate. |
| Approach: | They propose to use a 128-channel high-density EEG cap to evaluate EEG2Text models . they find existing benchmarks have neglected EEG instability, a flaw that has confounded inferences and sparked debate . |
| Outcome: | The proposed benchmarks provide key evidence for teacher-forcing-free decoding of EEG2Text models. |
Similar Papers
Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs) (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in NLP driven by powerful Large Language Models such as Ope-nAI GPT-4 have been demonstrated in ALS and stroke patients. |
| Approach: | They propose to use instruction-tuned Large Language Models (LLMs) with EEG data to decode and express brain activity in a comprehensible form. |
| Outcome: | The proposed approach enables multimodal description generation from EEG data and further refinement on embeddings to generate text directly from EMG during inference. |
Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder (2024.acl-long)
Copied to clipboard
| Challenge: | EEG-based language decoding is still in its nascent stages, despite promising applications in brain-computer interfaces. |
| Approach: | They propose a novel EEG-text Masked Autoencoder that orchestrates compound self-supervised learning across and within EEG and text through a dedicated multi-stream encoder. |
| Outcome: | The proposed model outperforms baseline framework in ROUGE-1 F1 and BLEU-4 scores and an LLM (specifically BART) to improve downstream tasks involving EEG and text. |
Rethinking Cross-Subject Data Splitting for Brain-to-Text Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have successfully decoded natural language from non-invasive brain signals . current dataset splitting methods suffer from data leakage problem . |
| Approach: | They propose a right cross-subject data splitting criterion without data leakage for decoding fMRI and EEG signal to text. |
| Outcome: | The proposed method overfits and overestimates brain-to-text decoding models. |
Decoding Part-of-Speech from Human EEG Signals (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that EEG signal magnitude and topography depend on word length, frequency and open vs. closed class. |
| Approach: | They propose to use EEG to predict Part-of-Speech (PoS) tags from neural signals measured at millisecond resolution during text reading. |
| Outcome: | The proposed techniques outperform linear-SVMs on PoS tagging of unigram and bigram data. |
Non-invasive electromyographic speech neuroprosthesis: a geometric perspective (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for mapping EMG to time-aligned audio limits applicability to patients who can no longer speak. |
| Approach: | They propose a neuromuscular speech interface that translates silently voiced articulations directly into text. |
| Outcome: | The proposed interface can translate silently voiced articulations directly into text without audio transfer . the proposed system could restore communication for patients with speech loss . |
The Language of Brain Signals: Natural Language Processing of Electroencephalography Reports (2020.lrec-1)
Copied to clipboard
| Challenge: | Clinical electroencephalography (EEG) is an excellent tool for probing neural function. |
| Approach: | They propose to use EEG to capture brain signals and its correlations with pathologies by a corpus of EEG reports to provide examples of EMG-specific concepts. |
| Outcome: | The proposed method provides examples of EEG-specific and clinically relevant concepts and exemplifies a self-attention joint-learning model to predict similar annotations in the EEG report corpus. |
BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Current EEG/MEG-to-text decoding systems rely on teacher-forcing methods . pre-trained large language models are over-dominant in decoding text from brain activity . |
| Approach: | They propose a framework that employs decoupled representation learning to achieve state-of-the-art performance on EEG and MEG datasets. |
| Outcome: | The proposed framework achieves state-of-the-art performance on EEG and MEG datasets. |
UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on decoding word-level fMRI volumes from a restricted vocabulary. |
| Approach: | They propose an open-vocabulary task to bridge fMRI time series and human language . they use a pre-trained language model to construct a robust encoder for cognitive signals . |
| Outcome: | The proposed task bridges fMRI time series and human language with a baseline model. |
The Limitations of Limited Context for Constituency Parsing (2021.acl-long)
Copied to clipboard
| Challenge: | a language model that is syntax-aware can produce better samples, authors say . a recent study shows that neural approaches to syntax can perform unsupervised syntactic parsing . |
| Approach: | They propose to incorporate syntax into neural approaches in NLP to produce better samples . they find that the first time neural approaches were able to perform unsupervised syntactic parsing . |
| Outcome: | The proposed models can perform unsupervised syntactic parsing, but they are lagging behind . the proposed models are based on a sandbox of probabilistic context-free-grammars . |
Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current methods for multimodal representation learning for electrocardiograms often result in suboptimal alignment of ECG signals with their corresponding text reports. |
| Approach: | They propose a framework to learn ECG representations by aligning ECG signals with paired free-text reports. |
| Outcome: | The proposed framework outperforms existing methods in zero-shot classification and linear probing tasks using 12 leads. |