Proceedings of the 3rd Workshop on Neural Generation and Translation
This document describes the findings of the Third Workshop on Neural Generation and Translation, held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019).
This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition quality. We validate these methods with several state-of-the-art textual style transfer methods. Higher quality of information decomposition corresponds to higher performance in terms of bilingual evaluation understudy (BLEU) between output and human-written reformulations.
This paper provides the reader with a report on 10th Russian Summer School in Information Retrieval (RuSSIR 2016).
The LOD Russia research project funded by the Ministry of Education aims to create a first Linked Open Data Set in Russia enabling scientists, researchers and commercial users to share, access, analyse and reuse knowledge related to scientific data. The position paper is highlighting challenges of the life-cycle management of LOD data, especially focuses on the process of entity linking and the creation of a unique identifier (UID) based on the concept of the Identification Knowledge Base (IKB).
This book constitutes the proceedings of the 7th International Conference on Analysis of Images, Social Networks and Texts, AIST 2018, held in Moscow, Russia, in July 2018.
The 29 full papers were carefully reviewed and selected from 107 submissions (of which 26 papers were rejected without being reviewed). The papers are organized in topical sections on natural language processing; analysis of images and video; general topics of data analysis; analysis of dynamic behavior through event data; optimization problems on graphs and network structures; and innovative systems.
Our current work is dedicated to research and development of methods for tutorial improvement and newcomers adaptation in online games. This report is focused on investigation of help-seeking patterns in online games’ chat logs. Using text mining techniques we detect game-related questions from users, explore their content, and show the changes across the server lifecycle.
The article is devoted to a review of the latest natural language processing (NLP) technologies that can be applied in strategic analytics. The introduction discusses the main problems in this area and specific tasks that can be solved using NLP tools. The article provides an overview of the main application areas in which these tools are involved. The paper reviews recent advancements in NLP and assess their potential. Conclusions are drawn about how the NLP apparatus should be developed in order to fulfill the needs of strategic analytics in the future.
Proceedings of the First Workshop on Subword and Character Level Models in NLP
Record linkage, or entity resolution, is an important area of data mining. Name matching is a key component of systems for record linkage. Alternative spellings of the same name are a common occurrence in many applications. We use the largest collection of genealogy person records in the world together with user search query logs to build namematching models. The procedure for building a crowd-sourced training set is outlined together with the presentation of our method. We cast the problem of learning alternative spellings as a machine translation problem at the character level. We use information retrieval evaluation methodology to show that this method substantially outperforms on our data a number of standard well known phonetic and string similarity methods in terms of precision and recall. Our result can lead to a significant practical impact in entity resolution applications.
The International Conference “Internet and Modern Society” (IMS-2020) was initially planned to take place in St. Petersburg, Russia. Due to the spread of COVID-19 and the ban on public events, the conference was held during 17-20 June 2020 in the format of online sessions with a discussion of papers and presentations uploaded in advance. The conference was organized by the ITMO University during the Information Society Week. The important events of IMS-2020, focused on specific aspects of information society and digital transformation, were International Workshop “Information Systems for Science and Education”, International Workshop “Internet Psychology” (IntPsy2020), International Workshop “Computational Linguistics” (CompLing2020) and International Workshop “ Electronic Governance ” (E-Governance2020).
The goal of the CompLing2020 workshop was to discuss the actual issues of interaction of linguistics and information technologies – regarding the development of technology solutions on the basis of a natural language, and the influence of information technologies on the language. Target audience are linguists of all profiles, the staff of organizations developing information systems that involve natural language processing, specialists in knowledge representation, higher education teachers, translators. The workshop was focused on the following key topics: Computer modeling of language, Computer analysis of natural language, Corpus linguistics, Digital linguistic resources, Computational and linguistic ontologies, Information extraction, Document analysis, Information retrieval, Machine translation, Computational lexicography, Speech technologies, Linguistic analysis of social networks.
This paper provides the reader with a report on 9th Russian Summer School in Information Retrieval (RuSSIR 2015).
We consider certain spaces of functions on the circle, which naturally appear in harmonic analysis, and superposition operators on these spaces. We study the following question: which functions have the property that each their superposition with a homeomorphism of the circle belongs to a given space? We also study the multidimensional case.
We consider the spaces of functions on the m-dimensional torus, whose Fourier transform is p -summable. We obtain estimates for the norms of the exponential functions deformed by a C1 -smooth phase. The results generalize to the multidimensional case the one-dimensional results obtained by the author earlier in “Quantitative estimates in the Beurling—Helson theorem”, Sbornik: Mathematics, 201:12 (2010), 1811 – 1836.
We consider the spaces of function on the circle whose Fourier transform is p-summable. We obtain estimates for the norms of exponential functions deformed by a C1 -smooth phase.