Tutorials
Diachronic word embeddings for semantic shifts modeling: how to trace changes of meaning in time
Andrey Kutuzov, University of Oslo
The tutorail will consist of two parts: a lecture and an exercise session. The lecture has no prerequisites and open to everybody. To participate in the exercise part a basic knowledge of Python is required. If you want to participate in the exercise session please bring with you a laptop with preinstalled Python 3.5 or higher and packages from this list: requirements.txt
Biography
Andrey Kutuzov is currently a doctoral research fellow at the University of Oslo, Norway. He holds a Masters degree in Computational Linguistics from the National Research University Higher School of Economics (Moscow, Russia). His industrial experience includes working with Lionbridge and Mail.ru Search.
Andrey has published papers at the top-tier international conference like EMNLP, ACL, CONLL, EACL and COLING. His primary research interest is using distributional word embedding models to trace long-term and short-term semantic shifts (see the survey paper on this).
Andrey is the leading maintainer of the RusVectōrēs project featuring various word embedding models for Russian and their visualizations. He teaches courses in NLP and deep learning at Masters level.
Biography
Andrey Kutuzov is currently a doctoral research fellow at the University of Oslo, Norway. He holds a Masters degree in Computational Linguistics from the National Research University Higher School of Economics (Moscow, Russia). His industrial experience includes working with Lionbridge and Mail.ru Search.
Andrey has published papers at the top-tier international conference like EMNLP, ACL, CONLL, EACL and COLING. His primary research interest is using distributional word embedding models to trace long-term and short-term semantic shifts (see the survey paper on this).
Andrey is the leading maintainer of the RusVectōrēs project featuring various word embedding models for Russian and their visualizations. He teaches courses in NLP and deep learning at Masters level.
Crowdsourcing for Language Resources and Evaluation
Dr. Dmitry Ustalov, Yandex
Crowdsourcing is an efficient approach for knowledge acquisition and data annotation that enables building impressive human-computer systems. In this tutorial, we will discuss the relations between Crowdsourcing and Natural Language Processing, focusing on its practical use for Language Resource construction and evaluation. We will describe the established genres of crowdsourcing, show their strengths and weaknesses on real-world examples and case studies, and provide recommendations for ensuring the high quality of the crowdsourced annotation.
Biography
Dmitry Ustalov works for Yandex at the Data Analysis and Research Group. In 2018 he defended his PhD thesis which he worked on at the Krasovskii Institute of Mathematics and Mechanics, Russia. His research interests are focused on Computational Lexical Semantics and Crowdsourcing. Before joining Yandex, Dmitry worked as a Post-Doctoral Research Fellow at the University of Mannheim, Germany and as a Teaching Assistant at the Ural Federal University, Russia.
Dr. Ustalov's research is published in premier international scientific journals and conferences, such as COLI, ACL, EACL, and EMNLP. He serves as a reviewer for COLI, SWJ, ACL, EMNLP, ISWC, and other publications. In 2012 Dmitry founded NLPub, the leading Russian wiki on Computational Linguistics. Also, he has been co-organizing the workshop and shared task on Russian Semantic Evaluation (RUSSE) since 2014 and the TextGraphs workshop since 2018.
Biography
Dmitry Ustalov works for Yandex at the Data Analysis and Research Group. In 2018 he defended his PhD thesis which he worked on at the Krasovskii Institute of Mathematics and Mechanics, Russia. His research interests are focused on Computational Lexical Semantics and Crowdsourcing. Before joining Yandex, Dmitry worked as a Post-Doctoral Research Fellow at the University of Mannheim, Germany and as a Teaching Assistant at the Ural Federal University, Russia.
Dr. Ustalov's research is published in premier international scientific journals and conferences, such as COLI, ACL, EACL, and EMNLP. He serves as a reviewer for COLI, SWJ, ACL, EMNLP, ISWC, and other publications. In 2012 Dmitry founded NLPub, the leading Russian wiki on Computational Linguistics. Also, he has been co-organizing the workshop and shared task on Russian Semantic Evaluation (RUSSE) since 2014 and the TextGraphs workshop since 2018.
Paper Presentations
Comparative Analysis of Scientific Papers Collections via Topic Modeling and Co-authorship Networks
Fedor Krasnov, Alexander Dimentov and Mikhail Shvartsman
Experimental Comparison of Unsupervised Approaches in the Task of Separating Specializations within Professions in Job Vacancies
Mikhail Vinel, Ivan Ryazanov, Dmitry Botov and Ivan Nikolaev
Effects of Training Data Size and Class Imbalance on the Performance of Classifiers
Wanwan Zheng and Mingzhe Jin
Soft Estimates of User Protection from Social Engineering Attacks: Fuzzy Combination of User Vulnerabilities and Malefactor Competencies in the Attacking Impact Success Prediction
Maxim Abramov and Alexander Tulupyev
Retrieval of Visually Shared News
Dmitrijs Milajevs
Usage of HMM-based Speech Recognition Methods for Automated Determination of a Similarity Level between Languages
Ansis Ataols Bērziņš
Binary Autoencoder for Text Modeling
Ruslan Baynazarov and Irina Piontkovskaya
Bi-LSTM Model for Morpheme Segmentation of Russian Words
Elena Bolshakova and Alexander Sapin
Prosodic Boundaries Prediction in Russian Using Morphological and Syntactic Features
Alla Menshikova and Daniil Kocharov
SentiRusColl: Russian Collocation Lexicon for Sentiment Analysis
Anastasia Kotelnikova and Evgeny Kotelnikov
An Approach to Abstractive Summarization for Norwegian Bokmål
Mariia Fedorova and Valentin Malykh
An Approach to Inter Annotator Agreement Evaluation for the Named Entity Recognition Task
Liliya Volkova and Viktor Bocharov
poster and demo session
POSTERS
Natural Language Processing and Machine Learning in the Big Data – Big Business project
Lili Aunimo and Janne Kauttonen
And Who Is To Judge: On Automatic Judgment Analysis
Vera Davydova, Anastasia Kravtsova, Maria Podryadchikova, Arina Reshetnikova
Machine Learning for Spectroscopic Data
Farid Hasanov
Linguistic Modeling as a Technique in Forensic Authorship Attribution
Anna Khomenko
Semi-Supervised Learning Approach in Bing Shopping Vertical to Increase Offer Coverage
Sachin Nagargoje
Entity Disambiguation to Wikipedia for Languages with Different Corpora Volumes
Irina Nikishina
Russian Diminutive Names Generation
Daria Rodionova
Experiments in Analysis of Industry-Academia Collaboration and Research Trends
Daniil Skorinkin, Irina Busurkina, Oleg Serikov
The Optimism Map of Russian News
Maria Tikhonova
Russian Word Sentiment Polarity Dictionary: a Publicly Available Dataset
Denis Kulagin
DEMO
Vec2graph: a Python Library for Visualizing Word Embeddings as Graphs
Nadezda Katricheva, Alyaxey Yaskevich, Anastasiya Lisitsina, Tamara Zhordaniya, Andrey Kutuzov, Elizaveta Kuzmenko
industrial session
Increasing the value and impact of NLP-based solutions. An overview of SILO.AI use cases and learnings from them.
Luiza Sayfullina, Silo.AI
Biography
Luiza Sayfullina is a senior Machine learning expert with 7+ years of Machine Learning experience having a deep understanding of Natural Language Processing for English and Finnish language. Proven track record from helping companies find and implement AI solutions ranging from low resource text classification, information extraction, summarization to speech-to-text applications. Organizer of ML study groups in Helsinki since 2016. PhD in Neural networks and Natural Language Processing from Aalto University (2019). Luiza's special interest lies also in the intersection of psychology and AI.
Luiza Sayfullina is a senior Machine learning expert with 7+ years of Machine Learning experience having a deep understanding of Natural Language Processing for English and Finnish language. Proven track record from helping companies find and implement AI solutions ranging from low resource text classification, information extraction, summarization to speech-to-text applications. Organizer of ML study groups in Helsinki since 2016. PhD in Neural networks and Natural Language Processing from Aalto University (2019). Luiza's special interest lies also in the intersection of psychology and AI.
Language Technology for Financial Markets
Dmitry Kan, AlphaSense Inc.
Biography
Dmitry Kan is the Head of Search with AlphaSense, premier business insights platform. Lately he has been focusing on Research projects. In his daily work he builds search algorithms, researching and using advances in Natural Language Processing and machine learning. In this talk Dmitry will explain the unique challenges for Language Technology as applied to financial domain. We will take a look at how our algorithms power the world's most fastest moving knowledge workers in a wide range of industries. Dmitry holds PhD in Computer Science from Saint Petersburg State University. His interests include search engines, sentiment analysis, recommender systems and language modelling.
Dmitry Kan is the Head of Search with AlphaSense, premier business insights platform. Lately he has been focusing on Research projects. In his daily work he builds search algorithms, researching and using advances in Natural Language Processing and machine learning. In this talk Dmitry will explain the unique challenges for Language Technology as applied to financial domain. We will take a look at how our algorithms power the world's most fastest moving knowledge workers in a wide range of industries. Dmitry holds PhD in Computer Science from Saint Petersburg State University. His interests include search engines, sentiment analysis, recommender systems and language modelling.
Building prompter bot with SOTA NLP
Darya Serdyuk and Alexey Karnachev, Just AI
Nowadays transformer architectures became really popular and also show great results as SOTA in various of NLP tasks. In our report we will talk about how we use transformer architecture for building prompter-like dialog system (system that offers the operator several answers). Also we'll cover business features and limitations that we have faced and how to overcome it and some ways to upgrade the results.
Darya and Alexey are NLP Research Engineers at Just AI with big experience in NLP field and especially in dialog systems.
Darya and Alexey are NLP Research Engineers at Just AI with big experience in NLP field and especially in dialog systems.
Feel free to contact us at ainlevent@gmail.com
2012-2022