Decoding Part-of-Speech from Human EEG Signals

Alex Murphy, Bernd Bohnet, Ryan McDonald, Uta Noppeney


Abstract
This work explores techniques to predict Part-of-Speech (PoS) tags from neural signals measured at millisecond resolution with electroencephalography (EEG) during text reading. We first show that information about word length, frequency and word class is encoded by the brain at different post-stimulus latencies. We then demonstrate that pre-training on averaged EEG data and data augmentation techniques boost PoS decoding accuracy for single EEG trials. Finally, applying optimised temporally-resolved decoding techniques we show that Transformers substantially outperform linear-SVMs on PoS tagging of unigram and bigram data.
Anthology ID:
2022.acl-long.156
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2201–2210
Language:
URL:
https://aclanthology.org/2022.acl-long.156
DOI:
10.18653/v1/2022.acl-long.156
Bibkey:
Cite (ACL):
Alex Murphy, Bernd Bohnet, Ryan McDonald, and Uta Noppeney. 2022. Decoding Part-of-Speech from Human EEG Signals. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2201–2210, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Decoding Part-of-Speech from Human EEG Signals (Murphy et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.156.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.156.mp4