Statistical Corpus and Language Comparison on Comparable Corpora

Eckart, Thomas; Quasthoff, Uwe

doi:10.1007/978-3-642-20128-8_8

Cited by 15 publications

(14 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An item (here, a word) x i has the probability P ( x i | x i −( n − 1) , …, x i −1 ). The text database was extracted from the Leipzig Corpora Collection, a ready to use corpora [33]. It contains a word frequency list as well as a word bi-grams list (co-occurrences as next neighbors) containing observed frequency counts, which were generated from approximately 1 million sentences publicly accessible.…”

Section: Methodsmentioning

confidence: 99%

Dynamic time window mechanism for time synchronous VEP-based BCIs—Performance evaluation with a dictionary-supported BCI speller employing SSVEP and c-VEP

et al. 2019

View full text Add to dashboard Cite

Brain-Computer Interfaces (BCIs) based on visual evoked potentials (VEPs) allow high communication speeds and accuracies. The fastest speeds can be achieved if targets are identified in a synchronous way (i.e., after a pre-set time period the system will produce a command output). The duration a target needs to be fixated on until the system classifies an output command affects the overall system performance. Hence, extracting a data window dedicated for the classification is of critical importance for VEP-based BCIs. Secondly, unintentional fixation on a target could easily lead to its selection. For the practical usability of BCI applications it is desirable to distinguish between intentional and unintentional fixations. This can be achieved by using threshold-based target identification methods. The study explores personalized dynamic classification time windows for threshold-based time synchronous VEP BCIs. The proposed techniques were tested employing the SSVEP and the c-VEP paradigm. Spelling performance was evaluated using an 8-target dictionary-supported BCI utilizing an n-gram word prediction model. The performance of twelve healthy participants was assessed with the information transfer rate (ITR) and accuracy. All participants completed sentence spelling tasks, reaching average accuracies of 94% and 96.3% for the c-VEP and the SSVEP paradigm, respectively. Average ITRs around 57 bpm were achieved for both paradigms.

show abstract

Section: Methodsmentioning

confidence: 99%

Dynamic time window mechanism for time synchronous VEP-based BCIs—Performance evaluation with a dictionary-supported BCI speller employing SSVEP and c-VEP

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The study is based on three sub-corpora generated in accordance with a set of common criteria: language, genre and size. As the corpora of differ-ent languages but similar genre allow language comparison (Eckart and Quasthoff, 2010), the compiled sub-corpora are of a similar size and composition and with matching structural features. Each sub-corpus contains the original texts in a specialised narrow domain of mechanical engineering, in particular authentic and highly regarded educational textbooks in three different languages and the Croatian National Termbank STRUNA (Table 1).…”

Section: Methodsmentioning

confidence: 99%

Collocations and Term Variation in Mechanical Engineering Discourse

Cigan¹

2018

Fluminensia (Online)

View full text Add to dashboard Cite

Terminological collocations1 are one of the most typical and very frequent units of representation of concepts in many disciplines. Although traditionally considered to be unwelcome in terminology, synonymy is amply present in specialized languages. Consequently, the same phenomenon is reflected in terminological collocations. This paper aims to investigate synonymous collocations extracted from mechanical engineering texts in terms of the most frequent and relevant types of denominative variation in the selected English collocations as well as of their equivalents in German and Croatian. The analysis of variations in terminological collocations gives insight into the (non)substitutability of collocation constituents as one of the major characteristics of collocations. Extracted collocations are analysed within a two-tier framework structured at a paradigmatic and a syntagmatic level, which allows for the identification of the three types of term variation: morphological, syntagmatic and semantic. Focusing on the collocations with the structure noun + noun and adjective + noun the results show that constituents of both syntactic structures allow substitution. The denominative variants are prevalent in adjective + noun collocations in which synonymous lexical elements functioning as collocates do not entail a concept change (admissible load ↔ allowable load). Lexeme substitutions are also annotated in noun + noun collocations expressing a slightly different dimension or facet of the concept (face gear vs. crown gear vs. crown wheel). The majority of German equivalents are nominal compounds that outnumber their morphological variants offering multiple equivalences.

show abstract

“…The prediction model was implemented using a frequency list and a bi-gram list from the Leipzig Corpora Collection 48 , which were based on approximately 1 million English sentences. After each selection, the www.nature.com/scientificreports/ suggestions were retrieved via structured query language (SQL).…”

Section: Spellersmentioning

confidence: 99%

Asynchronous c-VEP communication tools—efficiency comparison of low-target, multi-target and dictionary-assisted BCI spellers

Gembler

Benda

Rezeika

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Keyboards and smartphones allow users to express their thoughts freely via manual control. Hands-free communication can be realized with brain–computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs). Various variations of such spellers have been developed: Low-target systems, multi-target systems and systems with dictionary support. In general, it is not clear which kinds of systems are optimal in terms of reliability, speed, cognitive load, and visual load. The presented study investigates the feasibility of different speller variations. 58 users tested a 4-target speller and a 32-target speller with and without dictionary functionality. For classification, multiple individualized spatial filters were generated via canonical correlation analysis (CCA). We used an asynchronous implementation allowing non-control state, thus aiming for high accuracy rather than speed. All users were able to control the tested spellers. Interestingly, no significant differences in accuracy were found: 94.4%, 95.5% and 94.0% for 4-target spelling, 32-target spelling, and dictionary-assisted 32-target spelling. The mean ITRs were highest for the 32-target interface: 45.2, 96.9 and 88.9 bit/min. The output speed in characters per minute, was highest in dictionary-assisted spelling: 8.2, 19.5 and 31.6 characters/min. According to questionnaire results, 86% of the participants preferred the 32-target speller over the 4-target speller.

show abstract

Statistical Corpus and Language Comparison on Comparable Corpora

Cited by 15 publications

References 3 publications

Dynamic time window mechanism for time synchronous VEP-based BCIs—Performance evaluation with a dictionary-supported BCI speller employing SSVEP and c-VEP

Dynamic time window mechanism for time synchronous VEP-based BCIs—Performance evaluation with a dictionary-supported BCI speller employing SSVEP and c-VEP

Collocations and Term Variation in Mechanical Engineering Discourse

Asynchronous c-VEP communication tools—efficiency comparison of low-target, multi-target and dictionary-assisted BCI spellers

Contact Info

Product

Resources

About