Git Product home page Git Product logo

Hi there 👋

My name is Konstantin Sokolov, I'm a software developer with a background in Linguistics, Natural Language Processing, and R&D.

Notable Projects

  • Arranged and fulfilled transfer of technical infrastructure to AWS from Yandex Cloud to mitigate sanctions-related risks, which allowed undisturbed business operations in the global market. Secured AWS Activate funding for the AWS-based infrastructure of Evolwe project.
  • Established and led a national machine learning team in a large international company (AliExpress). Delivered multiple projects related to search and recommendation solutions for a large-scale international e-commerce platform.
  • A simulation project in the domain of transportation management targeted at scalable cloud-based infrastructure (OpenStack, AnyLogic), early stage research for a prominent logistics service provider Samokat.
  • A prototype syntactic annotation tool for OpenCorpora based on categorial grammar, parsing as deduction and proof assistant technology.
  • An interpreter for natural language commands for a smart home system based on OpenCCG semantic parser and a hybrid logic model checker.
  • A series of productivity and entertainment oriented virtual assistants for mobile platforms, including a Turing-100 winning virtual assistant Everfriends (originating from the dialogue manager backing «Eugene Goostman» chatbot).
  • National Corporate Internet Helper, a nation-wide self-care web application for corporate clients of Russian mobile network operator MTS.

Academic Professional Activities

  • Natural Language Understanding Reading Group (2013–2016), Peter the Great St. Petersburg Polytechnic University, organizer
  • Artificial Intelligence and Natural Language (AINL 2013, 2016), Artificial Intelligence and Natural Language & Information Extraction, Social Media and Web Search FRUCT Conference (AINL-ISMW FRUCT 2015), PC member
  • Artificial Intelligence and Natural Language (AINL 2012), St. Petersburg, Russia, co-organizer
  • Effective Training in Computational Linguistics, one-day industrial session, St. Petersburg State University, 2007, co-organizer

Teaching

  • Formal Methods in Natural Language Processing, a master’s level selective course covering topics in formal languages (mildly context-sensitive formalisms including CCG, TAG), Unification Grammar, Lambek calculus, parsing as deduction and computational semantics (Montague Grammar, DRT, LFG/Glue, type-theoretical semantics)
  • Statistical Natural Language Processing, covering language models, log-linear and MEMM models, tagging, constituency and dependency parsing, distributional semantics
  • Human-Computer Interaction, a selective course covering models of human performance, cognitive agents and cognitive architectures (incl. SOAR, Harmony Theory, seq2seq, Memory Networks, attention models)
  • Design of Software, a bachelor’s level course covering software design patterns and design for testability

Selected Publications

  • Konstantin Sokolov. A Vector Model for Type-Theoretical Semantics. Proceedings of the First Workshop on Representation Learning for NLP. ACL 2016. (pdf)
  • K. V. Sokolov, D. A. Timofeev, A. V. Samochadin. Process Extraction from Texts using Semantic Unification. In Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015) – Volume 3: KMIS. (pdf)
  • K. V. Sokolov, D. A. Timofeev, A. V. Samochadin. Extraction of Business Process Models from Texts. St. Petersburg State Polytechnical University Journal. Computer Science. Telecommunications and Control Systems, vol. 5 (229), 2015. (in Russian)
  • A. V. Andreev, O. A. Mitrofanova, K. V. Sokolov. Introduction to Formal Semantics. St. Petersburg State University, Faculty of Philology, 2014. (in Russian) (pdf)

Talks

  • Answer Set Programming in Natural Language Processing (FProg Meet-up, Yandex, St. Petersburg, 2012?)
  • Lambda Calculus in Lexical Semantics (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Dec 12, 2013)
  • R. Montague's Universal Grammar (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Dec 26, 2013)
  • R. Monatgue's PTQ Framework (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Feb 6, 2014)
  • Combinatorial Categorial Grammar, Hybrid Logic and Model Checking for Interpretation of Natural Language Commands in Smart Home Applications. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Mar 13, 2014)
  • Formalization of Locality in Typed Feature Structures. (XLIII International Philological Conference, St. Petersburg State University, Mar 11, 2014)
  • Topological Semantics for S4 Modal Logic System, part I (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Mar 20, 2014)
  • Topological Semantics for S4 Modal Logic System, part II (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Apr 3, 2014)
  • Neighborhood Grammar, part I (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Apr 24, 2014)
  • Neighborhood Grammar, part II (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, May 8, 2014)
  • Generalized Quantifiers (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, May 15, 2014)
  • J. Hintikka's Game-Theoretical Semantics (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, May 22, 2014)
  • Criticism of Formal Semantics by Cognitive Linguistics (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Sep 18, 2014)
  • Conceptual Systems in Cognitive Linguistics (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Oct 2, 2014)
  • What is a Cognitive Architecture? (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Oct 16, 2014)
  • Geometrical Approach to Semantics of Natural Language. P. Gaerdenfors' Conceptual Spaces. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Nov 13, 2014)
  • P. Smolensky's Harmony Theory. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Nov 27, 2014)
  • Harmonic Grammar, Optimality Theory and ICS Architecture. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Dec 4, 2014)
  • Distributed Representations for Analogical Reasoning. Hummel and Holyoak's LISA Architecture. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Dec 11, 2014)
  • What is Distributional Semantics? (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Feb 19, 2015)
  • Latent Semantic Analysis. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Mar 5, 2015)
  • Additive and Multiplicative Methods of Composition in Distributional Semantics. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Mar 19, 2015)
  • Functional Composition in Distributional Semantics. Baroni et al.'s "Frege in Space" Research Program. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Apr 2, 2015)
  • Neural Approaches to Composition in Distributional Semantics. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Apr 16, 2015)
  • Polylinear Algebra and Tensor Representations for Lexical Semantics. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Apr 30, 2015)
  • Pregroup Grammar and Diagram Languages for Tensor Calculus. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, May 14, 2015)
  • Category Theory in Compositional Distributional Semantics. Oxford Quantum Group's Research Program. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, May 28, 2015)
  • Computational Linguistics Research at Distributed Computation and Computer Networks Department, Peter the Great St. Petersburg Polytechnical University (FProg Meet-up, St. Petersburg, July 2015)
  • Type Theory and Lexical Semantics. An Overview. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Sep 17, 2015)
  • J. Pustejovsky's Generative Lexicon. Part I (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Oct 1, 2015)
  • J. Pustejovsky's Generative Lexicon, Type Theory and Lexical Decomposition. Part II (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Oct 15, 2015)
  • Type Theory with Records. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Oct 29, 2015)
  • Process Extraction From Texts Using Semantic Unification. (International Conference on Knowledge Management and Information Sharing, Nov 13, 2015)
  • Type Composition Logic. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Nov 26, 2015)
  • Dependent Type Semantics. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Dec 10, 2015)
  • Montagovian Generative Lexicon. (NLU Seminar, Peter the Great St. Petersburg Polytechnical University, Dec 24, 2015)
  • Attention Models for Chatbot Technology. Data Natives 2017, Berlin, Nov 16, 2017

Konstantin Sokolov's Projects

ccg-corpus icon ccg-corpus

Tools and syntactic annotation workplace (Java, Swing) for OpenCorpora

cl-toolbox icon cl-toolbox

A Parsing-as-Deduction system that parses with different parsing algorithms and some related tools for educational purposes.

fca icon fca

Implementation of NextClosure algorithm (Ganter, 1987) for Formal Concept Analysis (FCA)

hlmc icon hlmc

Hybrid Logic Model Checker (HLMC) and MCFull algorithm (Dragone, 2005) ported to Java

javafx-guice-mvp icon javafx-guice-mvp

Proof-of-concept architecture for JavaFX based on Dependency Injection, Model-View-Presenter (Passive View variant) and EventBus patterns

lm icon lm

Language modeling before it was mainstream

manifold-embeddings-s icon manifold-embeddings-s

A thin FastAPI wrapper over all-MiniLM-L6-v2 model for deployment in Docker. API similar to OpenAI Embeddings endpoint.

midterm icon midterm

Sample assignment for my NLP course at Peter the Great St. Petersburg Polytechnical University

nlu icon nlu

Natural Language Understanding group at Peter the Great St. Petersburg Polytechnic University

open-synsem icon open-synsem

Semantic interpretation of natural language commands with OpenCCG and Hybrid Logic

simple-lcg icon simple-lcg

A simplistic parser for Lambek Categorial Grammar based on term graphs, a variant of proof nets introduced in (Fowler 2016).

slides icon slides

Various TeX for my talks at Natural Language Understanding Reading Group (2013-2016)

textclassification icon textclassification

A Text Classification API in Java originally developed by DigitalPebble Ltd. The API is independent from the ML implementations used and can be used as a front end to various ML algorithms. libSVM and liblinear are currently embedded.

tweets-geolocation icon tweets-geolocation

PyTorch implementation of UnicodeCNN architecture from (Izbicki et al. Geolocating Tweets... 2019) for short texts geolocation

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.