Michal Stefanik's repositories
gensim_lda
LDA visualization of scientific papers referencing gensim
multimodal_learning
Preprocess Flickr dataset using important words extractor, pre-trained convolutional neural network and pre-trained Word2Vec to obtain corresponding representations. Project those representation into common space with different methods. Classify data into categories (one neural net and at least two other learning algorithms) and compare.
AWIR
Attention-weighted Information Retrieval system
mammoth
MAMMOTH: MAssively Multilingual Modular Open Translation @ Helsinki
mini-is
Automatically exported from code.google.com/p/mini-is
OneSecGame_03
third attempt on awesome clicking game
parser-z-xsd-schematu
Automated generator of XML schema for specific xml(s)
search-x
Extension of Calcformers for training to use search engine.
sentence-transformers
Sentence Embeddings with BERT & XLNet
stefanik12.github.io
Personal website