23 citations · 34 across the 7 of their papers we have counts for
8 papers
GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding
Konstantin Yakovlev, Alexander Podolskiy, Andrey Bout +2
Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models. However, approaches of this class are…
Sinkhorn Transformations for Single-Query Postprocessing in Text-Video Retrieval
Konstantin Yakovlev, Gregory Polyakov, Ilseyar Alimova +4
A recent trend in multimodal retrieval is related to postprocessing test set results via the dual-softmax loss (DSL). While this approach can bring significant improvements, it usu…
PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing
Xiaozhe Ren, Pingyi Zhou, Xinfan Meng +14
The scaling of large language models has greatly improved natural language understanding, generation, and reasoning. In this work, we develop a system that trained a trillion-param…
Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution
Nikolay Arefyev, Boris Sheludko, Alexander Podolskiy +1
Lexical substitution, i.e. generation of plausible words that can replace a particular target word in a given context, is an extremely powerful technology that can be used as a bac…
Boundary control and homogenization: optimal climatization through smart double skin boundaries
J. I. Díaz, A. V. Podolskiy, T. A. Shaposhnikova
We consider the homogenization of an optimal control problem in which the control is placed on a part of the boundary and the spatial domain contains a thin layer of "small particl…
Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection
Alexander Podolskiy, Dmitry Lipin, Andrey Bout +2
Real-life applications, heavily relying on machine learning, such as dialog systems, demand out-of-domain detection methods. Intent classification models should be equipped with a…
A Comparative Study of Lexical Substitution Approaches based on Neural Language Models
Nikolay Arefyev, Boris Sheludko, Alexander Podolskiy +1
Lexical substitution in context is an extremely powerful technology that can be used as a backbone of various NLP applications, such as word sense induction, lexical relation extra…
Homogenization of a net of periodic critically scaled boundary obstacles related to reverse osmosis "nano-composite" membranes
Jesús Ildefonso Díaz, David Gómez-Castro, Alexander V. Podolskiy +1
One of the main goals of this paper is to extend some of the mathematical techniques of some previous papers by the authors showing that some very useful phenomenological propertie…