SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.01512 · 2024

MAD: Multi-Alignment MEG-to-Text Decoding

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
neuspeech/mad-meg2text canonical 12 of 13
FunctionStatusWhere it lives
change_sampling_rate Ran neuspeech/mad-meg2text/data_augmentation_utils/eeg_aug.py
code served (permissive licence) · get_code("434a023482ca36fa")
compute_accuracy Ran neuspeech/mad-meg2text/utils/model_utils.py
code served (permissive licence) · get_code("262947201dc066e9")
cosine_similarity Ran neuspeech/mad-meg2text/utils/loss.py
code served (permissive licence) · get_code("38ede58bd9091f21")
cut_signal Ran neuspeech/mad-meg2text/data_augmentation_utils/eeg_aug.py
code served (permissive licence) · get_code("9b5228012d8f05df")
inter_class_relation Ran neuspeech/mad-meg2text/utils/loss.py
code served (permissive licence) · get_code("b45038694ef6bb75")
match_modules Ran neuspeech/mad-meg2text/utils/load_model.py
code served (permissive licence) · get_code("bf84bf80d676a07a")
match_modules_string Ran neuspeech/mad-meg2text/utils/load_model.py
code served (permissive licence) · get_code("1c6ebf4c6f313f2c")
multi_segment_speed_change Ran neuspeech/mad-meg2text/data_augmentation_utils/eeg_aug.py
code served (permissive licence) · get_code("5f0ebfcfa62171f4")
pad_multiple Ran neuspeech/mad-meg2text/utils/brain_module.py
code served (permissive licence) · get_code("4ecb4c91cf8f4446")
pearson_correlation Ran neuspeech/mad-meg2text/utils/loss.py
code served (permissive licence) · get_code("d00eea76cc523c64")
preprocess_text Ran neuspeech/mad-meg2text/evaluation.py
code served (permissive licence) · get_code("2908e3c7f6faafb0")
projection_module Ran neuspeech/mad-meg2text/utils/model_utils.py
code served (permissive licence) · get_code("db94765af5a0e4dd")
concatenate_images Not yet run neuspeech/mad-meg2text/wandb_callback.py
code served (permissive licence) · get_code("ac8331082a4cff98")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deciphering language from brain activity is a crucial task in brain-computer interface (BCI) research. Non-invasive cerebral signaling techniques including electroencephalography (EEG) and magnetoencephalography (MEG) are becoming increasingly popular due to their safety and practicality, avoiding invasive electrode implantation. However, current works under-investigated three points: 1) a predominant focus on EEG with limited exploration of MEG, which provides superior signal quality; 2) poor performance on unseen text, indicating the need for models that can better generalize to diverse linguistic contexts; 3) insufficient integration of information from other modalities, which could potentially constrain our capacity to comprehensively understand the intricate dynamics of brain activity. This study presents a novel approach for translating MEG signals into text using a speech-decoding framework with multiple alignments. Our method is the first to introduce an end-to-end multi-alignment framework for totally unseen text generation directly from MEG signals. We achieve an impressive BLEU-1 score on the \textit{GWilliams} dataset, significantly outperforming the baseline from 5.49 to 6.86 on the BLEU-1 metric. This improvement demonstrates the advancement of our model towards real-world applications and underscores its potential in advancing BCI research. Code is available at $\href{https://github.com/NeuSpeech/MAD-MEG2text}{https://github.com/NeuSpeech/MAD-MEG2text}$.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.01512")
get_code_for_paper("2406.01512")
have("2406.01512")

Connect an agent — have() is free.