arXiv subjects

Vladimir Ivanov

Publications and source records attributed to Vladimir Ivanov.

32 records · Page 2Linked to original sources

arXiv2020

RuREBus: a Case Study of Joint Named Entity Recognition and Relation Extraction from e-Government Domain

We show-case an application of information extraction methods, such as named entity recognition (NER) and relation extraction (RE) to a novel corpus, consisting of documents, issued by a state agency. The main challenges of this corpus are: 1) the annotation scheme differs greatly from the one used for the general domain corpora, and 2) the documents are written in a language other than English. Unlike expectations, the state-of-the-art transformer-based models show modest performance for both tasks, either when approached sequentially, or in an end-to-end fashion. Our experiments have demonstrated that fine-tuning on a large unlabeled corpora does not automatically yield significant improvement and thus we may conclude that more sophisticated strategies of leveraging unlabelled texts are demanded. In this paper, we describe the whole developed pipeline, starting from text annotation, baseline development, and designing a shared task in hopes of improving the baseline. Eventually, we realize that the current NER and RE technologies are far from being mature and do not overcome so far challenges like ours.

cs.CL↗

arXiv2020

Inno at SemEval-2020 Task 11: Leveraging Pure Transformer for Multi-Class Propaganda Detection

The paper presents the solution of team "Inno" to a SEMEVAL 2020 task 11 "Detection of propaganda techniques in news articles". The goal of the second subtask is to classify textual segments that correspond to one of the 18 given propaganda techniques in news articles dataset. We tested a pure Transformer-based model with an optimized learning scheme on the ability to distinguish propaganda techniques between each other. Our model showed 0.6 and 0.58 overall F1 score on validation set and test set accordingly and non-zero F1 score on each class on both sets.

cs.CL↗

arXiv2020

SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations

Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations. The ability to capture relations within data can provide the much needed inductive bias necessary for building more robust Machine Learning algorithms with more interpretable results. In this paper, inspired by recent advances in relational learning using Graph Neural Networks, we propose the Self-Attention Graph Variational AutoEncoder (SAG-VAE) network which can simultaneously learn feature relations and data representations in an end-to-end manner. SAG-VAE is trained by jointly inferring the posterior distribution of two types of latent variables, which denote the data representation and a shared graph structure, respectively. Furthermore, we introduce a novel self-attention graph network that improves the generative capabilities of SAG-VAE by parameterizing the generative distribution allowing SAG-VAE to generate new data via graph convolution, while still trainable via backpropagation. A learnable relational graph representation enhances SAG-VAE's robustness to perturbation and noise, while also providing deeper intuition into model performance. Experiments based on graphs show that SAG-VAE is capable of approximately retrieving edges and links between nodes based entirely on feature observations. Finally, results on image data illustrate that SAG-VAE is fairly robust against perturbations in image reconstruction and sampling.

cs.LG↗

arXiv2020

So What's the Plan? Mining Strategic Planning Documents

In this paper we present a corpus of Russian strategic planning documents, RuREBus. This project is grounded both from language technology and e-government perspectives. Not only new language sources and tools are being developed, but also their applications to e-goverment research. We demonstrate the pipeline for creating a text corpus from scratch. First, the annotation schema is designed. Next texts are marked up using human-in-the-loop strategy, so that preliminary annotations are derived from a machine learning model and are manually corrected. The amount of annotated texts is large enough to showcase what insights can be gained from RuREBus.

cs.CL↗

arXiv2020

Realistic Physics Based Character Controller

Over the course of the last several years there was a strong interest in application of modern optimal control techniques to the field of character animation. This interest was fueled by introduction of efficient learning based algorithms for policy optimization, growth in computation power, and game engine improvements. It was shown that it is possible to generate natural looking control of a character by using two ingredients. First, the simulated agent must adhere to a motion capture dataset. And second, the character aims to track the control input from the user. The paper aims at closing the gap between the researchers and users by introducing an open source implementation of physics based character control in Unity framework that has a low entry barrier and a steep learning curve.

cs.AI↗

arXiv2019

Towards Federated Learning at Scale: System Design

Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralized data. We have built a scalable production system for Federated Learning in the domain of mobile devices, based on TensorFlow. In this paper, we describe the resulting high-level design, sketch some of the challenges and their solutions, and touch upon the open problems and future directions.

cs.LG↗

arXiv2018

A Neural-Astrocytic Network Architecture: Astrocytic calcium waves modulate synchronous neuronal activity

Understanding the role of astrocytes in brain computation is a nascent challenge, promising immense rewards, in terms of new neurobiological knowledge that can be translated into artificial intelligence. In our ongoing effort to identify principles endow-ing the astrocyte with unique functions in brain computation, and translate them into neural-astrocytic networks (NANs), we propose a biophysically realistic model of an astrocyte that preserves the experimentally observed spatial allocation of its distinct subcellular compartments. We show how our model may encode, and modu-late, the extent of synchronous neural activity via calcium waves that propagate intracellularly across the astrocytic compartments. This relationship between neural activity and astrocytic calcium waves has long been speculated but it is still lacking a mechanistic explanation. Our model suggests an astrocytic "calcium cascade" mechanism for neuronal synchronization, which may empower NANs by imposing periodic neural modulation known to reduce coding errors. By expanding our notions of information processing in astrocytes, our work aims to solidify a computational role for non-neuronal cells and incorporate them into artificial networks.

q-bio.NC↗

arXiv2018

Toward a Better Understanding of How to Develop Software Under Stress - Drafting the Lines for Future Research

The software is often produced under significant time constraints. Our idea is to understand the effects of various software development practices on the performance of developers working in stressful environments, and identify the best operating conditions for software developed under stressful conditions collecting data through questionnaires, non-invasive software measurement tools that can collect measurable data about software engineers and the software they develop, without intervening their activities, and biophysical sensors and then try to recreated also in different processes or key development practices such conditions.

cs.SE↗

arXiv2017

A tool for visualizing the execution of programs and stack traces especially suited for novice programmers

Software engineering education and training have obstacles caused by a lack of basic knowledge about a process of program execution. The article is devoted to the development of special tools that help to visualize the process. We analyze existing tools and propose a new approach to stack and heap visualization. The solution is able to overcome major drawbacks of existing tools and suites well for analysis of programs written in Java and C/C++.

cs.SE↗

arXiv2017

An architecture for non-invasive software measurement

Analysis of data related to software development helps to increase quality, control and predictability of software development processes and products.However, collecting such data for is a complex task. A non-invasive collection of software metrics is one of the most promising approaches to solve the task. In this paper we present an approach which consists of four parts: collect the data, store all collected data, unify the stored data and analyze the data to provide insights to the user about software product or process. We employ the approach to the development of an architecture for non-invasive software measurement system and explain its advantages and limitations.

cs.SE↗

arXiv2016

Practical Secure Aggregation for Federated Learning on User-Held Data

Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregation protects each user's model gradient. We design a novel, communication-efficient Secure Aggregation protocol for high-dimensional data that tolerates up to 1/3 users failing to complete the protocol. For 16-bit input values, our protocol offers 1.73x communication expansion for $2^{10}$ users and $2^{20}$-dimensional vectors, and 1.98x expansion for $2^{14}$ users and $2^{24}$ dimensional vectors.

cs.CR↗

arXiv2012

2D atom localization in a four-level tripod system in laser fields

We propose a scheme for two-dimensional (2D) atom localization in a four-level tripod system under an influence of two orthogonal standing-wave fields. Position information of the atom is retained in the atomic internal states by an additional probe field either of a standing or of a running wave. It is shown that the localization factors depend crucially on the atom-field coupling that results in such spatial structures of populations as spikes, craters and waves. We demonstrate a high-precision localization due to measurement of population in the upper state or in any ground state.

physics.atom-ph↗

arXiv2003

Kerov's central limit theorem for the Plancherel measure on Young diagrams

Consider random Young diagrams with a fixed number n of boxes, where the probability distribution on diagrams is determined by the Plancherel measure. That is, the weight of a diagram is proportional to the squared dimension of the corresponding irreducible representation of the symmetric group S_n. As n goes to infinity, the boundary of the (suitably scaled) random diagram concentrates near a curve Omega (Logan-Shepp 1977, Vershik-Kerov 1977). In 1993, Kerov announced a central limit theorem describing Gaussian fluctuations of random diagrams around the limit shape Omega. Here we propose a reconstruction of his proof, largely based on Kerov's unpublished work notes (1999). We also discuss a striking similarity between Kerov's result and central limit theorems for random matrices (Diaconis-Shahshahani, Johansson).

math.CO↗

arXiv2003

The Algebra of Conjugacy Classes in Symmetric Groups and Partial Permutations

We prove a convolution formula for the conjugacy classes in symmetric groups conjectured by the second author. A combinatorial interpretation of coefficients is provided. As a main tool we introduce new semigroup of partial permutations. We describe its structure, representations, and characters. We also discuss filtrations on the subalgebra of invariants in the semigroup algebra.

math.CO↗