-
Patterns versus Characters in Subword-aware Neural Language Modeling
Words in some natural languages can have a composite structure. Elements...
09/02/2017 ∙ by Rustem Takhanov, et al. ∙
0
∙
share
read it
-
Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones
Syllabification does not seem to improve word-level RNN language modelin...
07/20/2017 ∙ by Zhenisbek Assylbekov, et al. ∙
0
∙
share
read it
-
Searching for an algebra on CSP solutions
The Constraint Satisfaction Problem (CSP) is a problem of computing a ho...
08/28/2017 ∙ by Rustem Takhanov, et al. ∙
0
∙
share
read it
-
Reusing Weights in Subword-aware Neural Language Models
We propose several ways of reusing subword embeddings and other weights ...
02/23/2018 ∙ by Zhenisbek Assylbekov, et al. ∙
0
∙
share
read it
-
Fourier analysis perspective for sufficient dimension reduction problem
A theory of sufficient dimension reduction (SDR) is developed from an op...
08/19/2018 ∙ by Rustem Takhanov, et al. ∙
0
∙
share
read it
-
Context Vectors are Reflections of Word Vectors in Half the Dimensions
This paper takes a step towards theoretical analysis of the relationship...
02/26/2019 ∙ by Zhenisbek Assylbekov, et al. ∙
0
∙
share
read it
-
Fourier Neural Networks: A Comparative Study
We review neural network architectures which were motivated by Fourier s...
02/08/2019 ∙ by Abylay Zhumekenov, et al. ∙
0
∙
share
read it
-
Dimension reduction as an optimization problem over a set of generalized functions
Classical dimension reduction problem can be loosely formulated as a pro...
03/12/2019 ∙ by Rustem Takhanov, et al. ∙
0
∙
share
read it
-
Semantics- and Syntax-related Subvectors in the Skip-gram Embeddings
We show that the skip-gram embedding of any word can be decomposed into ...
12/23/2019 ∙ by Maxat Tezekbayev, et al. ∙
0
∙
share
read it
