Pinned Repositories
Advanced-Machine-Learning-Specialization
Advanced Machine Learning Specialization on Coursera
BookShop
Coursework in the second year in which it was necessary to develop and design a database (a mandatory block) and make an application to work with it (an optional task to get an assessment). For the second part, the site was written in JavaScript.
CHW-Team
Course-certificates
Certificates of my courses
Courses
My files of courses in Coursera and Stepick
CourseWork
My course work with the database
DataProcessing
control homework
JetBrains-Academy
Projects proposed in JetBrains Academy
Prediction-of-LOS
My course work aimed on prediction of length of stay at the clinics
SemEval-2021-ToxicSpansDetection
In the field of Natural Language Processing, the detection of text toxicity has become a significant challenge. To facilitate the research in this sphere, one of the tasks of the International Workshop on Semantic Evaluation 2021 is Toxic Spans Detection. The essential objective of this task is to identify toxic spans within English passages. In this paper, two approaches for toxic spans detection considered: Machine Reading Comprehension and modified Named Entity Recognition approach altogether with Machine Reading Comprehension, but also these approaches are improved by Question Generation method. Furthermore, this research presents the exploratory analysis of provided data, proposes a training process and examines the analysis of the results on F1-score of new state-of-the-art BERT-based Language Models: BERT, ALBERT, RoBERTa, XLM-RoBERTa and SpanBERT. Finally, the best language model obtained an F1-score of 0.688 on the test data.
dmitrytsyu's Repositories
dmitrytsyu/SemEval-2021-ToxicSpansDetection
In the field of Natural Language Processing, the detection of text toxicity has become a significant challenge. To facilitate the research in this sphere, one of the tasks of the International Workshop on Semantic Evaluation 2021 is Toxic Spans Detection. The essential objective of this task is to identify toxic spans within English passages. In this paper, two approaches for toxic spans detection considered: Machine Reading Comprehension and modified Named Entity Recognition approach altogether with Machine Reading Comprehension, but also these approaches are improved by Question Generation method. Furthermore, this research presents the exploratory analysis of provided data, proposes a training process and examines the analysis of the results on F1-score of new state-of-the-art BERT-based Language Models: BERT, ALBERT, RoBERTa, XLM-RoBERTa and SpanBERT. Finally, the best language model obtained an F1-score of 0.688 on the test data.
dmitrytsyu/Advanced-Machine-Learning-Specialization
Advanced Machine Learning Specialization on Coursera
dmitrytsyu/BookShop
Coursework in the second year in which it was necessary to develop and design a database (a mandatory block) and make an application to work with it (an optional task to get an assessment). For the second part, the site was written in JavaScript.
dmitrytsyu/CHW-Team
dmitrytsyu/Course-certificates
Certificates of my courses
dmitrytsyu/Courses
My files of courses in Coursera and Stepick
dmitrytsyu/CourseWork
My course work with the database
dmitrytsyu/DataProcessing
control homework
dmitrytsyu/JetBrains-Academy
Projects proposed in JetBrains Academy
dmitrytsyu/Prediction-of-LOS
My course work aimed on prediction of length of stay at the clinics
dmitrytsyu/github-slideshow
A robot powered training repository :robot:
dmitrytsyu/iad-deep-learning
Курс "Современные методы машинного обучения" на майноре ИАД
dmitrytsyu/Introduction-to-deep-learning
This repository contains Ipython notebooks from the course 'Introduction to deep learning', part 1 of Advance machine learning Specialisation offered by higher school of economics at coursera.
dmitrytsyu/ML-Azure
Azure homework
dmitrytsyu/WoofTwo
New version