No abstract

Hearing loss is determined by the diapason change of perceived ear sound frequencies and intensity. Cochlear tonotopicity represents the relationship between stimulation frequency f and place ℓ along the cochlea by the equation of the acoustic-wave hearing model at before-receptors stage ℓ(f) = Lo.22log(f/fmo), where Lo = 32 mm – the cochlear duct length, fmo = 20 kHz – maxima frequency of audible sound. Age-related frequencies standards can be represented by f(t)=fmoe–rt, where r=0.01 year–1 – high-frequency loss factor sound. Using both relations together, we get the length of the cochlear duct for T years LT = Lo.22log(fT/fmo). Destruction of the cochlear duct is exposed apex experiencing cyclical exposure to sound, which represents a decline of frequency fmo. The real length of the cochlear duct LR determined by the same ratio at a frequency fT = fmaxR, established audiometric. Treatment (pharmacological or physical therapy) causes a change in the physical and audiometric properties of inner ear structures. Daily monitoring of the upper frequency sound (fmaxX) determines the effective (useful) the length of the cochlear duct LX. Value LX/LR can be a criterion of treatment effectiveness: LX/LR →1 when the treatment is effective.

No abstract

No abstract

Article in EnglishFor citation: Abdullin Y.B., Ivanov V.V. Deep learning model for bilingual sentiment classification of short texts. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2017, vol. 17, no. 1, pp. 129-136. doi: 10.17586/2226-1494-2017 Abstract Sentiment analysis of short texts such as Twitter messages and comments in news portals is challenging due to the lack of contextual information. We propose a deep neural network model that uses bilingual word embeddings to effectively solve sentiment classification problem for a given pair of languages. We apply our approach to two corpora of two different language pairs: English-Russian and Russian-Kazakh. We show how to train a classifier in one language and predict in another. Our approach achieves 73% accuracy for English and 74% accuracy for Russian. For Kazakh sentiment analysis, we propose a baseline method, that achieves 60% accuracy; and a method to learn bilingual embeddings from a large unlabeled corpus using a bilingual word pairs. Аннотация Исследованы проблемы классификации коротких текстов (сообщения в Twitter, комментарии из новостных порталов) при недостатке контекстной информации. Предложена модель глубокой нейронной сети, использующей двуязычные векторные представления слов для эффективного решения проблемы классификации тональности текста конкретной пары языков. Предложенный подход применен к двум корпусам двух различных языковых пар: английский-русский и русский-казахский. Показан способ обучения классификатора на одном языке и применения его для предсказывания тональности на другом. Предлагаемый подход позволил достичь 73% точности для английского языка и 74% точности для русского языка. Впервые получены результаты анализа тональности на казахском языке с точностью до 60%. Предложен метод создания двуязычных векторных представлений слов из больших неразмеченных корпусов с использованием словаря переводов.