Michał Marcińczuk's Projects
Collection of tools, snippets and resources related to CUDA
Inforex is a web system for text corpora construction.
Config files for my GitHub profile.
Instruction and resources to build a morfeusz2 package for form generation required by Polem
Evaluation of Named Entity Recognition Tools
Scripts for evaluation of named entity recognition
Heuristic-based approach to post-correction of OCR-results for Polish.
Tech.io playground
Tool for named entity recognition for Polish based on deep learning.
Polish News Model Project
Transformer-based model for punctuation restoration for Polish (PolEval 2021 submission)
Collection of Python scripts related to natural language processing
Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
SnaPy is a Python library for detecting near duplicate texts using Locality Sensitive Hashing.
Tensor representaiton of text
Named Entity Recognition with Pretrained XLM-Roberta