Papers by Dmitry Karpov

4 papers
TheRuSLan: Database of Russian Sign Language (2020.lrec-1)

Copied to clipboard

Challenge: The database is the first of a kind for Russian sign language and is intended for use in machine learning, gesture recognition and sign language linguistics.
Approach: They present a Russian sign language multimedia database called TheRuSLan . the database includes lexical units from Russian sign languages within one subject area .
Outcome: The proposed database includes lexical units from Russian sign language within one subject area.
DeepPavlov 1.0: Your Gateway to Advanced NLP Models Backed by Transformers and Transfer Learning (2024.emnlp-demo)

Copied to clipboard

Challenge: Open-source framework for using NLP models is released for non-experts . complexity of building, fine-tuning and deploying state-of-the-art models remains a barrier .
Approach: They present DeepPavlov 1.0, an open-source framework for using NLP models . the framework is based on PyTorch and supports HuggingFace transformers .
Outcome: The DeepPavlov 1.0 framework is designed for practitioners with limited knowledge of NLP/ML.
RUSAVIC Corpus: Russian Audio-Visual Speech in Cars (2022.lrec-1)

Copied to clipboard

Challenge: a new audio-visual speech corpus is recorded in a car environment and is noise-robust . currently there is no noiserobustic speech recognition system to be used in real-driving conditions.
Approach: They propose to use a natural speech corpus recorded in a car environment to improve audio-based speech recognition in the presence of severe acoustic noise.
Outcome: The proposed corpus is natural, controlled and adequate size to train state-of-the-art NN approaches.
DeepPavlov Dream: Platform for Building Generative AI Assistants (2023.acl-demo)

Copied to clipboard

Challenge: open-source DeepPavlov Dream Platform is designed for development of complex dialog systems . platform supports modular approach to implementation of conversational agents .
Approach: open-source DeepPavlov Dream Platform is designed for development of complex dialog systems . platform includes a conversational orchestrator called DeepPvlov Agent to coordinate asynchronous dialog pipeline .
Outcome: The open-source DeepPavlov Dream Platform is designed for development of complex dialog systems like Generative AI Assistants.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations