Lost in Conversation: A Conversational Agent Based on the Transformer and Transfer Learning
Golovanov S., Tselousov A., Rauf Kurbanov, Sergey I Nikolenko
Research of heuristic approaches for determining the tonality of text messages in natural language processing problems
, , , , in : Proceedings of 2019 XVI International Symposium "Problems of Redundancy in Information and Control Systems" (REDUNDANCY). : IEEE, 2019. P. 159-164.
Determining the tonality of the text is a difficult task, the solution of which essentially depends on the context, the field of study and the amount of text data. The analysis shows that the authors in their works do not jointly use the full range of possible transformations on the data and their combinations. The ...
Added: September 20, 2020
Cham : Springer, 2019
Intelligent Systems Conference (IntelliSys) 2018 is the fourth research conference in the series. This conference is a part of SAI conferences being held since 2013. The conference series has featured keynote talks, special sessions, poster presentation, tutorials, workshops, and contributed papers each year. The conference focus on areas of intelligent systems and artificial intelligence (AI) and ...
Added: August 29, 2018
, , in : The Palgrave Handbook of Digital Russia Studies. : Palgrave Macmillan, 2021. Ch. 26. P. 465-481.
Deep learning is a term used to describe artificial intelligence (AI) technologies. AI deals with how computers can be used to solve complex problems in the same way that humans do. Such technologies as computer vision (CV) and natural language processing (NLP) are distinguished as the largest AI areas. To imitate human vision and the ...
Added: December 20, 2020
, , , in : Analysis of Images, Social Networks and Texts. 9th International Conference, AIST 2021, Moscow, Russia, December 16 – 18, 2021, Revised Selected Papers. Vol. 12345w: LNCS.: Springer Publishing Company, 2022. P. 1-10.
The ubiquity of the contemporary language understanding tasks gives relevance to the development of generalized, yet highly efficient models that utilize all knowledge, provided by the data source. In this work, we present SocialBERT - the first model that uses knowledge about the author’s position in the network during text analysis. We investigate possible models ...
Added: October 31, 2021
Intelligent Data Processing 11th International Conference, IDP 2016, Barcelona, Spain, October 10–14, 2016, Revised Selected Papers
Switzerland : Springer, 2019
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 ...
Added: February 8, 2020
The Russian Drug Reaction Corpus and Neural Models for Drug Reactions and Effectiveness Detection in User Reviews
, , et al., Bioinformatics 2021 Vol. 37 No. 2 P. 243-249
Drugs and diseases play a central role in many areas of biomedical research and healthcare. Aggregating knowledge about these entities across a broader range of domains and languages is critical for information extraction (IE) applications. To facilitate text mining methods for analysis and comparison of patient’s health conditions and adverse drug reactions reported on the ...
Added: January 13, 2021
, , , Expert Systems with Applications 2021 Vol. 183 No. 30 November 2021 P. 1-13
Social media platforms are considered one of the most effective intermediaries for companies to interact with consumers. Social media-based decision support systems for the marketing domain are highly developed, but product development and innovation-oriented studies remain limited. This study offers a novel approach which utilises opinion retrieval theme along with sentiment analysis to support the ...
Added: December 12, 2021
, , , in : Analysis of Images, Social Networks and Texts. 7th International Conference AIST 2018. : Springer, 2018. Ch. 12. P. 121-126.
This paper deals with automatic classification of questions in the Russian language. In contrast to previously used methods, we introduce a convolutional neural network for question classification. We took advantage of an existing corpus of 2008 questions, manually annotated in accordance with a pragmatic 14-class typology. We modified the data by reducing the typology to ...
Added: February 15, 2019
, , et al., Informatsionno-upravliaiushchie sistemy [Information and Control Systems] 2020 No. 1 P. 2-14
Introduction: Sentiment analysis is a complex problem whose solution essentially depends on the context, field of study and amount of text data. Analysis of publications shows that the authors often do not use the full range of possible data transformations and their combinations. Only a part of the transformations is used, limiting the ways to ...
Added: February 20, 2020
Association for Computational Linguistics, 2019
The 4th Workshop on Representation Learning for NLP (RepL4NLP) will be hosted by ACL 2019 and held on 2 August 2019. The workshop is being organised by Isabelle Augenstein, Spandana Gella, Sebastian Ruder, Katharina Kann, Burcu Can, Alexis Conneau, Johannes Welbl, Xian Ren and Marek Rei; and advised by Kyunghyun Cho, Edward Grefenstette, Karl Moritz ...
Added: November 1, 2019
Analysis of Images, Social Networks and Texts. 10th International Conference AIST 2021, Tbilisi, Georgia, December 16–18, 2021, Revised Selected Papers. (Lecture Notes in Computer Science)
Cham : Springer, 2022
This book constitutes revised selected papers from the 9th International Conference on Analysis of Images, Social Networks and Texts, AIST 2020, held during December 16-18, 2021. The world of Data Science changes every year. At AIST, we exchange our understanding of the Science state-of-the-art, as well as how it applies to life and business. AIST ...
Added: January 4, 2022
, , , , in : Analysis of Images, Social Networks and Texts: 9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020, Revised Selected Papers. Vol. 12602.: Springer, 2021. P. 149-161.
We present a novel dataset of sports broadcasts with 8,781 games. The dataset contains 700 thousand comments and 93 thousand related news documents in Russian. We run an extensive series of experiments of modern extractive and abstractive approaches. The results demonstrate that BERT-based models show modest performance, reaching up to 0.26 ROUGE-1F-measure. In addition, human evaluation ...
Added: May 10, 2021
, , et al., , in : Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. : Association for Computational Linguistics, 2019. P. 6053-6058.
Large-scale pretrained language models define state of the art in natural language processing, achieving outstanding performance on a variety of tasks. We study how these architectures can be applied and adapted for natural language generation, comparing a number of architectural and training schemes. We focus in particular on open-domain dialog as a typical high entropy ...
Added: February 20, 2021
The performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. The rapidly developing field of representation learning is concerned with questions surrounding how we can best learn meaningful and useful representations of data. We take a broad view of the field and include ...
Added: October 31, 2018
, , et al., Frontiers in Genetics 2021 Article 638191
We propose a method for generating an electrocardiogram (ECG) signal for one cardiac cycle using a variational autoencoder. Our goal was to encode the original ECG signal using as few features as possible. Using this method we extracted a vector of new 25 features, which in many cases can be interpreted. The generated ECG has ...
Added: October 29, 2021
Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог» (Москва, 29 мая — 1 июня 2019 г.)
М. : Издательский центр «Российский государственный гуманитарный университет», 2019
The book includes 64 papers submitted to the International conference in computer linguistics and intellectual technologies Dialogue 2019 and presents a broad spectrum of theoretical and applied research of natural language description, language simulation, and creation of applied computer technologies. ...
Added: October 16, 2019
, , et al., , in : Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021). : Association for Computational Linguistics, 2021. P. 1249-1254.
This work describes our approach for subtasks of SemEval-2021 Task 8: MeasEval: Counts and Measurements which took the official first place in the competition. To solve all subtasks we use multi-task learning in a question-answering-like manner. We also use learnable scalar weights to weight subtasks’ contribution to the final loss in multi-task training. We fine-tune ...
Added: September 23, 2021
, , , , in : Analysis of Images, Social Networks and Texts. 6th International Conference, 2017, Revised Selected Papers. Vol. 10716.: Cham : Springer, 2018. Ch. 4. P. 34-46.
The paper deals with Google’s universal parser SyntaxNet. The system was used to analyze the Universal Dependencies linguistic corpora. We conducted an error analysis of the output of the parser to reveal to what extent the error types are connected with or preconditioned by the language types. In particular, we carried out several experiments, clustering ...
Added: December 1, 2017
, , Foresight and STI Governance 2016 Vol. 10 No. 1 P. 69-82
The objective of this paper is to analyse the scope for improving the empirical and methodological foundation of global value chains (GVCs) research and for making relevant political decisions, primarily through applying Foresight methodology. The authors review the major trends of global value chains’ development, specific features of Russia’s participation in them, and the necessary ...
Added: July 12, 2016
, , et al., , in : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019). : IEEE, 2019. P. 9601-9611.
We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of surfaces and curves allows ...
Added: November 26, 2019
, В кн. : Электронный бизнес. Управление интернет-проектами. Инновации: Сборник трудов участников студенческой научно-практической конференции, Москва, 12-14 марта 2013 г. : М. : НИУ ВШЭ, 2014. С. 88-91.
The report deals with the methodology of building a system to perform search for specialists satisfying a defined set of competencies. The proposed search method is based on natural language texts analysis. ...
Added: July 11, 2015
, , , Economic Research-Ekonomska Istraživanja 2022 Vol. 35 No. 1 P. 122-142
This article contributes to the development of contestable market theory by investigating how competitiveness in the eSports industry influences the size of this industry, as measured by the volume of monetary prizes. We use data on each gamer's prize earnings for each tournament from 1999 to 2015 to estimate panel vector autoregression (VAR) model with ...
Added: April 22, 2021
, В кн. : Современные проблемы информатизации в анализе и синтезе технологических и программно-телекоммуникационных систем: Сборник трудов. Вып. 17.: Воронеж : Научная книга, 2012. С. 264-266.
Added: November 7, 2012
, , et al., , in : Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2020). Vol. 4.: SciTePress, 2020. P. 214-221.
We propose a novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism. The user control ability allows to explicitly specify the texture which should be generated by the model. This property follows from using an encoder part which learns a latent representation for each texture from the dataset. To ensure ...
Added: November 8, 2020