blazejdolicki

bert-sarcasm-detection

Sarcasm detection with BERT

CargoLoading

The programme finds an optimal packing configuration for a container with dimensions 33 x 8 x 5 via different methods - simple greedy search, backtracking and divide & conquer. There is also a sophisticated maximal layers algorithm which isn't fully implemented. After choosing the way of packing the container the programme displays the solution using JavaFX 3D. The whole report with all details is available here: https://goo.gl/RpDKf9 It was my university group project, which I developed in January 2018, therefore not all of the code was written by myself.

CHEDAR

Code for our paper "CHEDAR: Conversation History Embedding for Dense Answer Retrieval."

multilingual-analysis

Code for my Bachelor's thesis "Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer"

pytorch-templates

PyTorch templates to reuse in new projects

advent-of-code-2018

bottom-up-attention.pytorch

An PyTorch reimplementation of bottom-up-attention models

multilingual-interference

Code for a project about tackling negative interference in multilingual meta-learning setup.

nfl-big-data-bowl-2020

nlp2-language-emergence

Code for our short paper "Image classification pressures in language emergence"

data-clinics

My assignments for the Data Analysis course that I attended in Spring 2020 as part of my bachelor's degree.

data-madness

databricks_repo

Databricks related python and powershell code

deepface

A Lightweight Deep Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Framework for Python

EGG

EGG: Emergence of lanGuage in Games

GolfBot

Project 1-2

ham4corpus

Data from "Hamilton: An American Musical", formatted for reuse. See below for some interesting text analysis basic findings! I am not throwing away my stopword?

LASER

Language-Agnostic SEntence Representations

LearningLanguageApp

The programme is mostly an exercise, where user can translate random words from one language to another. In case user doesn't know how to translate it, he can use a clue. After finishing the exercise, he can see his overall results. Writing a word correctly in the exercise hugely decreases the probability of its occurrence in the next sessions.

metrics

Machine learning metrics for distributed, scalable PyTorch applications.

multifit

The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model Fine-tuning" https://arxiv.org/abs/1909.04761

pandas_exercises

Practice your pandas skills!

production-app-fastai

Starter app for fastai v3 model deployment on Render

TetrisBot

The programme is a Tetris game. There is a mode in which the game is played by a bot which uses genetic algorithms to optimize his performance. It was an university group project I worked on at the end of 2017, therefore not all of the code was written by myself.

udify

A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.

uva-fact-ai-course

This repository contains implementations of algorithms proposed in recent papers from top machine learning conferences on Fairness, Accountability, Confidentiality, and Transparency (FACT). These were implemented as part of the FACT-AI course at the University of Amsterdam.

uvadlc_practicals_2020

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.