Модели и методы интерактивного взаимодействия с вычислительными устройствами нового поколения
The article examines the issue of developing models of the text input methods. The urgency of this matter is dictated by the reduction of financial costs of designing new input methods and upgrading existing ones. The article suggests a modeling method, which is verified by a series of experiments. Also the article gives recommendations on the use of the suggested modeling method.
The book includes 61 reports of the International conference on computer and intellectual technology "Dialogue-2019", representing a wide range of theoretical and applied research in the field of natural language description, modeling of language processes, creating practically applicable computer linguistic technologies. For specialists in the field of theoretical and applied linguistics and intellectual technologies.
In this paper, we consider several compression techniques for the language modeling problem based on recurrent neural networks (RNNs). It is known that conventional RNNs, e.g., LSTM-based networks in language modeling, are characterized with either high space complexity or substantial inference time. This problem is especially crucial for mobile applications, in which the constant interaction with the remote server is inappropriate. By using the Penn Treebank (PTB) dataset we compare pruning, quantization, low-rank factorization, tensor train decomposition for LSTM networks in terms of model size and suitability for fast inference.
Mobile Ecosystems have been related to products, or to a community of developers around a product and gives the certain advantages to the platform owners and participants of the ecosystem. The paper answers the question -- what are the existing approaches to build mobile ecosystems, who are the participants and what are their benefits?
We explore recently introduced definition modeling technique that provided the tool for evaluation of different distributed vector representations of words through modeling dictionary definitions of words. In this work, we study the problem of word ambiguities in definition modeling and propose a possible solution by employing latent variable modeling and soft attention mechanisms. Our quantitative and qualitative evaluation and analysis of the model shows that taking into account words ambiguity and polysemy leads to performance improvement.
We consider certain spaces of functions on the circle, which naturally appear in harmonic analysis, and superposition operators on these spaces. We study the following question: which functions have the property that each their superposition with a homeomorphism of the circle belongs to a given space? We also study the multidimensional case.
We consider the spaces of functions on the m-dimensional torus, whose Fourier transform is p -summable. We obtain estimates for the norms of the exponential functions deformed by a C1 -smooth phase. The results generalize to the multidimensional case the one-dimensional results obtained by the author earlier in “Quantitative estimates in the Beurling—Helson theorem”, Sbornik: Mathematics, 201:12 (2010), 1811 – 1836.
We consider the spaces of function on the circle whose Fourier transform is p-summable. We obtain estimates for the norms of exponential functions deformed by a C1 -smooth phase.