Publications

This volume contains the refereed proceedings of the 8th International Conference on Analysis of Images, Social Networks, and Texts (AIST 2019). The previous conferences during 2012–2018 attracted a significant number of data scientists – students, researchers, academics, and engineers working on interdisciplinary data analysis of images, texts, and social networks.

The paper addresses the questions of data science education of current importance. It aims to introduce and justify the framework that allows flexibly evaluate the processes of a data expedition and a digital media created during it. For these purposes, the authors explore features of digital media artefacts which are specific to data expeditions and are essential to accurate evaluation. The rubrics as a power but hardly formalizable evaluation method in application to digital media artefacts are also discussed. Moreover, the paper documents the experience of rubrics creation according to the suggested framework. The rubrics were successfully adopted to two data-driven journalism courses. The authors also formulate recommendations on data expedition evaluation which should take into consideration structural features of a data expedition, distinctive features of digital media, etc.

The chapter presents novel approaches to predict and control buckling of thin-walled structures; mathematically, these approaches are formalized as the first and second inverse bifurcation problems for von Karman equations. Both approaches are based upon the method employed to solve the direct bifurcation problem for the equations in question. The approach considered was applied to several difficult problems of actual practice, viz., for the first inverse problem, to the problems of optimal thickness distribution and optimal external pressure distribution for a cylindrical shell, optimal curvature for a cylindrical panel as well; for the second inverse problem, to the problem to predict buckling of a cylindrical shell under an external pressure.

This article is devoted to the issue of developing adaptive learning systems for vocational education and training (VET). Firstly, it justifies the urgency of developing and using personalized adaptive learning in vocational educational organizations. Specific features of the Russian VET system and its students are described, demonstrating a number of arguments for the importance of a search for new digital educational solutions. Secondly, the paper elaborates on the theoretical framework of personalization of vocational education and training, which takes into account the necessity for both skills and knowledge. Finally, the authors present a prototype of an adaptive educational system, which is based on ontologically-controlled management of learning trajectories. The developed software is aimed at improving the effectiveness of the VET material science curriculum.

Catherine Meadows has played an important role in the advancement of formal methods for protocol security verification. Her insights on the use of, for example, narrowing and rewriting logic has made possible the automated discovery of new attacks and the shaping of new protocols. Meadows has also investigated other security aspects, such as, distance-bounding protocols and denial of service attacks. We have been greatly inspired by her work. This paper describes the use of Multiset Rewriting for the specification and verification of timing aspects of protocols, such as network delays, timeouts, timed intruder models and distance-bounding properties. We detail these timed features with a number of examples and describe decidable fragments of related verification problems.

This book constitutes the post-conference proceedings of the 8th International Conference on Analysis of Images, Social Networks and Texts, AIST 2019, held in Kazan, Russia, in July 2019.

The 27 full and 8 short papers were carefully reviewed and selected from 134 submissions (of which 21 papers were automatically rejected without being reviewed). The papers are organized in topical sections on general topics of data analysis; natural language processing; social network analysis; analysis of images and video; optimization problems on graphs and network structures; and analysis of dynamic behavior through event data.

A multichannel attribution model based on gradient boost- ing over trees is proposed, which was compared with the state of the art models: bagged logistic regression, Markov chains approach, shapely value. Experiments on digital advertising datasets showed that the pro- posed model is better than the solutions considered by ROC AUC metric. In addition, the problem of probability prediction of conversion by the consumer using the ensemble of the analyzed algorithms was solved, the meta-features obtained were enriched with consumers and offline activities of the advertising campaign data.

It has recently been shown that first-order- and datalog-rewritability of ontology-mediated queries (OMQs) with expressive ontologies can be checked in NExpTime using a reduction to CSPs. In this paper, we present a case study for OMQs with Boolean conjunctive queries and a fixed ontology consisting of a single covering axiom 𝐴 -> 𝐹 v 𝑇, A -> F v T, possibly supplemented with a disjointness axiom for T and F. The ultimate aim is to classify such OMQs according to their data complexity: AC0, L, NL, P or coNP. We report on our experience with trying to distinguish between OMQs in P and coNP using the reduction to CSPs and the Polyanna software for finding polymorphisms.

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications. In this paper we consider several compression techniques for recurrent neural networks including Long–Short Term Memory models. We make particular attention to the high-dimensional output problem caused by the very large vocabulary size. We focus on effective compression methods in the context of their exploitation on devices: pruning, quantization, and matrix decomposition approaches (low-rank factorization and tensor train decomposition, in particular). For each model we investigate the trade-off between its size, suitability for fast inference and perplexity. We propose a general pipeline for applying the most suitable methods to compress recurrent neural networks for language modeling. It has been shown in the experimental study with the Penn Treebank (PTB) dataset that the most efficient results in terms of speed and compression–perplexity balance are obtained by matrix decomposition techniques.

We introduce a concept of a virtualdiscourse treeto improve question answering (Q/A) recall for complex, multi-sentence questions. Augmenting thediscourse tree of an answer with tree fragments obtained from text corpora playing the role of ontology, we obtain on the flya canonical discourse representation of this answer that is independent of thethought structure of a given author. This mechanism is critical for finding an answer that is not only relevant in terms of questions entities but also in terms of inter-relations between these entities in an answer and its style. We evaluate the Q/A system enabled with virtualdiscourse trees and observe a substantial increase of performanceanswering complex questions such as Yahoo! Answers and www.2carpros.com.

We present a study on co-authorship network representation based on network embedding together with additional information on topic modeling of research papers and new edge embedding operator. We use the link prediction (LP) model for constructing a recommender system for searching collaborators with similar research interests. Extracting topics for each paper, we construct keywords co-occurrence network and use its embedding for further generalizing author attributes. Standard graph feature engineering and network embedding methods were combined for constructing co-author recommender system formulated as LP problem and prediction of future graph structure. We evaluate our survey on the dataset containing temporal information on National Research University Higher School of Economics over 25 years of research articles indexed in Russian Science Citation Index and Scopus. Our model of network representation shows better performance for stated binary classification tasks on several co-authorship networks.

Reduction of the number of parameters is one of the most important goals in Deep Learning. In this article we propose an adaptation of Doubly Stochastic Variational Inference for Automatic Relevance Determination (DSVI-ARD) for neural networks compression. We find this method to be especially useful in language modeling tasks, where large number of parameters in the input and output layers is often excessive. We also show that DSVI-ARD can be applied together with encoder-decoder weight tying allowing to achieve even better sparsity and performance. Our experiments demonstrate that more than 90% of the weights in both encoder and decoder layers can be removed with a minimal quality loss.

This paper discusses the scientific and practical perspectives of using general game playing in business-to-business price negotiations as a part of Procurement 4.0 revolution. The status quo of digital price negotiations software, which emerged from intuitive solutions to business goals and refereed to as electronic auctions in industry, is summarized in a scientific context. Description of such aspects as auctioneers’ interventions, asymmetry among players and time- depended features reveals the nature of nowadays electronic auctions to be rather termed as price games. This paper strongly suggests general game playing as the crucial technology for automation of human rule setting in those games. Game theory, genetic programming, experimental economics, and AI human player simulation are also discussed as satellite topics. SIDL-type game descriptions languages and their formal game-theoretic foundations are presented.

Co-authorship networks represent a graph, in which vertices are authors, and edges represent research papers written in co-authorship. Every paper could generate several edges in such a graph, if a number of coauthors is greater than two. Co-authorship networks play important role in understanding the structure of research collaborations usually resulted in joint research papers. Moreover, when analyzing university ranking and research staff publishing activity, coauthorship network may help identifying both, efficient research communities and also people, who lack proper collaborators while having poor research results. Our paper is devoted to the visualization and interpretation of the former sets using as an example co-authorship network of National Research University Higher School of Economics (HSE), Moscow, Russia, while we also discuss the possible solutions for recommending collaborators for the latter set of researchers with low academic profile. Our paper is a case study for our university, which can be extended to larger co-authorship networks using research indexing services.

Customer support systems based on chatbots gain an increasing popularity. Chatbots are becoming more and more important to a plethora of applications not only for social services. Modern information retrieval (IR) chatbots are based on simple queries to a database and do not ensure intelligent dialogues with users. In this paper we propose an IR-chatbot model that incorporates a concept-based knowledge model and an index-guided traversal through it to ensure the discovery of information relevant for users and coherent to their preferences. The proposed approach not only supports a search session, but also helps users to discover properties of items and sequentially refine an imprecise query.

This book constitutes the refereed proceedings of the 11th International Conference on Intelligent Data Processing, IDP 2016, held in Barcelona, Spain, in October 2016.  

The 11 revised full papers were carefully reviewed and selected from 52 submissions. The papers of this volume are organized in topical sections on machine learning theory with applications; intelligent data processing in life and social sciences; morphological and technological approaches to image analysis.

There are many different methods for computing relevant patterns in sequential data and interpreting the results. In this paper, we compute emerging patterns (EP) in demographic sequences using sequence-based pattern structures, along with different algorithmic solutions. The purpose of this method is to meet the following domain requirement: the obtained patterns must be (closed) frequent contiguous prefixes of the input sequences. This is required in order for demographers to fully understand and interpret the results.

There are many different methods for computing relevant patterns in sequential data and interpreting the results. In this paper, we compute emerging patterns (EP) in demographic sequences using sequence-based pattern structures, along with different algorithmic solutions. The purpose of this method is to meet the following domain requirement: the obtained patterns must be (closed) frequent contiguous prefixes of the input sequences. This is required in order for demographers to fully understand and interpret the results.

In this paper, we study the problem of predicting quantity of collaborations in co-authorship network. We formulated our task in terms of link prediction problem on weighted co-authorship network, formed by authors writing papers in co-authorship represented by edges between authors in the network. Our task is formulated as regression for edge weights, for which we use node2vec network embedding and new family of edge embedding operators. We evaluate our model on AMiner co-authorship network and showed that our model of network edge representation has better performance for stated regression link prediction task.