Language Model Applications to Spelling with  Brain-Computer Interfaces

Mora-Cortes, Anderson; Manyakov, Nikolay V.; Chumerin, Nikolay; Hulle, Marc M. Van

doi:10.3390/s140405967

Cited by 38 publications

(34 citation statements)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the accuracy and speed of the system can be increased through mechanisms like this implemented dictionary or other language-based models (see e.g. the review [17]). The number of commands needed to complete the spelling tasks increased on average by a factor of 1.92, if the previously developed three-step spelling application (without dictionary [8]) was used instead (see C * n / C n in Table 1).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A User-Friendly Dictionary-Supported SSVEP-based BCI Application

Stawicki

Gembler

Volosyak

2017

Symbiotic Interaction

View full text Add to dashboard Cite

Abstract. A brain-computer interface (BCI) measures and interprets brain signals enabling people to communicate without the use of peripheral muscles. One of the common BCI paradigms are steady state visual evoked potentials (SSVEPs), brain signals induced by gazing at a constantly flickering target. The choice of stimulation frequencies and the number of simultaneously used stimuli highly influence the performance of such SSVEP-based BCI. In this article, a dictionary-driven four class SSVEP-based spelling application is presented, tested, and evaluated. To enhance classification accuracy, frequencies were determined individually with a calibration software for SSVEP-BCIs, enabling non-experts to set up the system. Forty-one healthy participants used the BCI system to spell English sentences (lengths between 23 and 37 characters). All participants completed the spelling task successfully. A mean accuracy of 97.92% and a mean ITR of 23.84 bits/min were achieved, 18 participants even reached 100% accuracy. On average the number of commands needed to spell the example sentences with four classes, without dictionary support is higher by a factor of 1.92. Thanks to the implemented dictionary the time needed to spell typical everyday sentences can be drastically reduced.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Various BCI spelling interfaces with built-in dictionaries have already been developed by different research groups [17].…”

mentioning

confidence: 99%

A User-Friendly Dictionary-Supported SSVEP-based BCI Application

Stawicki

Gembler

Volosyak

2017

Symbiotic Interaction

View full text Add to dashboard Cite

show abstract

“…To reduce the prediction time of the next letter in the sequence, one approach is to incorporate language models into AAC devices (Vertanen and Kristensson, 2011), and BCI in particular (Mora-Cortes et al, 2014). The potential advantage of combining a language model with EEG information in a BCI system is twofold: achieving higher accuracy of target predictions, as well as gains in the speed of the process of typing the user's intended string (Speier et al, 2011;Orhan et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

“…It may also help with reducing the number of necessary stimuli required for symbol selection (Speier et al, 2016). Mora-Cortes et al (2014) describe different types of EEG responses common when employing a typing-based BCI, and in the review of Speier et al (2016), event-related potentials (ERP) seem to be the prevailing choice in particular. In the RSVP-Keyboard (Orhan et al, 2012), an ERP signal is elicited in response to a rapid display of letters.…”

Section: Introductionmentioning

confidence: 99%

“…Maintaining more than one candidate may reduce frustration among users, and minimize time spent correcting errors. We also, as recommended by Mora-Cortes et al (2014) and Speier et al (2016), explicitly incorporate word-level information and mix word-level and character-level language models to improve letter level prediction. Notably, this approach allows our system to support out-of-vocabulary (OOV) words.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the Second Workshop on Subword/Character LEvel Models

2018

View full text Add to dashboard Cite

ii Introduction Traditional NLP starts with a hand-engineered layer of representation, the level of tokens or words. A tokenization component first breaks up the text into units using manually designed rules. Tokens are then processed by components such as word segmentation, morphological analysis and multiword recognition. The heterogeneity of these components makes it hard to create integrated models of both structure within tokens (e.g., morphology) and structure across multiple tokens (e.g., multi-word expressions). This approach can perform poorly (i) for morphologically rich languages, (ii) for noisy text, (iii) for languages in which the recognition of words is difficult and (iv) for adaptation to new domains; and (v) it can impede the optimization of preprocessing in end-to-end learning.The workshop provides a forum for discussing recent advances as well as future directions on sub-word and character-level natural language processing and representation learning that address these problems. Topics of Interest:• tokenization-free models• character-level machine translation• character-ngram information retrieval• transfer learning for character-level models• models of within-token and cross-token structure• NL generation (of words not seen in training etc)• out of vocabulary words• morphology and segmentation• relationship b/w morphology and character-level models• stemming and lemmatization • inflection generation• orthographic productivity• form-meaning representations• true end-to-end learning AbstractNeural machine translation has achieved impressive results in the last few years, but its success has been limited to settings with large amounts of parallel data. One way to improve NMT for lower-resource settings is to initialize a word-based NMT model with pretrained word embeddings. However, rare words still suffer from lower quality word embeddings when trained with standard word-level objectives. We introduce word embeddings that utilize morphological resources, and compare to purely unsupervised alternatives. We work with Arabic, a morphologically rich language with available linguistic resources, and perform Ar-to-En MT experiments on a small corpus of TED subtitles. We find that word embeddings utilizing subword information consistently outperform standard word embeddings on a word similarity task and as initialization of the source word embeddings in a low-resource NMT system.

show abstract