Name: Jekaterina Novikova
Type: User
Bio: Research in Natural Language Processing, Machine Learning, Trustworthy AI.
Twitter: J_Novikova_NLP
Location: Toronto, Canada
Blog: https://jeknov.github.io
Jekaterina Novikova's Projects
100 days of algorithms
35 days of solving algorithm problems
An open-source NLP research library, built on PyTorch.
A curated awesome list of resources from the bots/AI world by BotCube team. Join our newsletter to get five epic actionable bot tricks delivered to your inbox once a week! 🤖 ❤️
A curated list of papers and resources about the consistency of large language models.
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表,主要面向基础大模型评测,旨在探求生成式AI的技术边界.
:book: A curated list of resources dedicated to Natural Language Processing (NLP)
A curated list of awesome R packages, frameworks and software.
TensorFlow - A curated list of dedicated resources http://tensorflow.org
Supplementary material accompanying the following paper: Jekaterina Novikova (2021). Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text.
Beyond the Imitation Game collaborative benchmark for enormous language models
Weblog’s basic functionality is a possibility to write, read, edit and delete posts, write and delete comments. Additional functionality is user registration with a confirmation of registration
A proposal for creating a reflective listening chatbot
Repo for the Data Scientist’s Toolbox course project
The Leek group guide to data sharing
The E2E NLG Challenge Dataset
Selections from EMNLP 2020
The dataset and statistical analysis code released with the submission of EMNLP 2017 paper "Why We Need New Evaluation Metrics for NLG"
ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.
Gender recognition from static pictures by neural network and PCA algorithm
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
The dataset released with the submission of INLG 2016 paper "Crowd-sourcing NLG Data: Pictures Elicit Better Data" (https://aclweb.org/anthology/W/W16/W16-6644.pdf)
Huge update! Interactive Python coding interview challenges (algorithms and data structures). Includes Anki flashcards.