Ahmed, Salman, Singh, Muskaan, Bhattacharyya, Saugat and Coyle, Damien (2024) Decoding neural activity for part-of-speech tagging (POS). In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 01-04 October 2023, Honolulu, Oahu, HI, USA.

Full text not available from this repository. (Request a copy)

Abstract

Decoding Part of Speech(POS) tagging directly from electroencephalography (EEG) signals whilst user overtly spoke (voiced speech) sentences could improve direct speech brain-computer interfaces (BCIs) using imagined or inner speech. To the best of our knowledge, earlier work uses machine learning approach using 74,953 sentences/tokens recorded in 75 EEG sessions. The tokens can be found in 4,479 phrases consisting of terms from the English Online treebank which contains the record of weblogs, newsgroups, reviews, and Yahoo Answers. The results demonstrated the feasibility of POS decoding from EEG based on word class, word frequency, and word length with accuracy of 71%, 86%, 89%, respectively. We believe that there is significant room for improvement with more advanced artificial intelligence. In this paper, we further extend the existing work with end-to-end transformers. Our results presents transformer model outperforms benchmark traditional ML results with +20% in length, +13% for the open vs closed class and +12% in frequency. In our empirical analysis, we find the decoding performance was better when using multi-electrode recordings as compared to single-electrode recordings.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	part of speech, POS, Decoding neural activity, electroencephalograph, EEG, brain-computer interfaces, BCIs
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Divisions:	Other Departments (Central units) > Research & Enterprise
Depositing User:	Salman Ahmed
Date Deposited:	05 Feb 2024 12:01
Last Modified:	05 Feb 2024 12:01
URI:	https://oars.uos.ac.uk/id/eprint/3581

Actions (login required)

View Item