Roman Grundkiewicz's repositories
gec-scripts
A set of scripts for processing data for grammatical error correction
morfologik
Ruby MRI bindings for morfologik-stemming library.
news-translit-nmt
Training scripts and instructions how to reproduce our systems submitted to the NEWS 2018 Task on Transliteration of Named Entities: R. Grundkiewicz, K. Heafield: Neural Machine Translation Techniques for Named Entity Transliteration, NEWS 2018, ACL
autozoil-jenkins
Autozoil Jenkins Plugin
keyboard_distance
Distance-on-keyboard algorithm implementation for Ruby.
preprocess
Corpus preprocessing
psi-website
The official website of the Information Systems Laboratory
ape-filter
Scripts for TER filtering
crowd-alone
Crowd-sourcing System-level MT Evaluations
geccla
It will be added later.
intgemm
int8_t and int16_t matrix multiply based on https://arxiv.org/abs/1705.01991
marian-dev
Fast Neural Machine Translation in C++ - development repository
mosesdecoder
Moses, the machine translation system
OCELoT
Project OCELoT: an Open, Collaborative Evaluation Leaderboard of Translations
polish_chars
Extension of Ruby String class by handling Polish diacritics.
python-code-validator
Runs black, mypy, pylint, reorder-python-imports and safety
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
wmt-format-tools
Tools for formatting WMT hypothesis and test sets in XML
yarescorer
Yet another n-best list re-scorer