Language Technology at the University of Helsinki

All

106 repositories

LLM-course-2024
Public
Repository for the course Large Language Models and Generative AI for NLP
Jupyter Notebook
•13•10•0•1•Updated Nov 26, 2024Nov 26, 2024
swag_transformers
Public
Python
•
MIT License
•0•0•0•0•Updated Nov 26, 2024Nov 26, 2024
mammoth
Public
MAMMOTH: MAssively Multilingual Modular Open Translation @ Helsinki
Python
•
MIT License
•3•22•12•1•Updated Nov 25, 2024Nov 25, 2024
OpusIndex
Public
Python
•0•0•0•0•Updated Nov 15, 2024Nov 15, 2024
OpusDistillery
Public
Training pipelines for Firefox Translations neural machine translation models (adapted for OPUS-MT and integrating GreenNLP metrics)
Python
•
Mozilla Public License 2.0
•34•2•8•0•Updated Nov 15, 2024Nov 15, 2024
swa_gaussian
Public
Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning" (Helsinki-NLP fork)
Jupyter Notebook
•
BSD 2-Clause "Simplified" License
•82•0•0•0•Updated Nov 13, 2024Nov 13, 2024
OPUS
Public
The Open Parallel Corpus
JavaScript
•7•58•10•0•Updated Nov 10, 2024Nov 10, 2024
lm-vs-mt
Public
A Comparison of Language Modeling and Translation as Multilingual Pretraining Objectives
machine-translation language-modeling pretraining multilingual-nlp
Python
•0•1•0•0•Updated Nov 9, 2024Nov 9, 2024
shroom
Public
SCSS
•0•4•0•0•Updated Nov 8, 2024Nov 8, 2024
OPUS-CAT
Public
OPUS-CAT is a collection of software which make it possible to OPUS-MT neural machine translation models in professional translation. OPUS-CAT includes a local offline MT engine and a collection of CAT tool plugins.
natural-language-processing language-translation machine-translation language-technology computer-assisted-translation computer-aided-translation translation-tool
C#
•
MIT License
•11•70•46•8•Updated Nov 1, 2024Nov 1, 2024
KD4MT-survey
Public
TeX
•0•0•0•0•Updated Nov 1, 2024Nov 1, 2024
External-MT-leaderboard
Public
Leaderboards for external MT models
Creative Commons Attribution Share Alike 4.0 International
•0•1•1•0•Updated Oct 18, 2024Oct 18, 2024
OPUS-MT-leaderboard
Public
Makefile
•
Creative Commons Attribution Share Alike 4.0 International
•1•1•4•0•Updated Oct 18, 2024Oct 18, 2024
OPUS-MT-dashboard
Public
PHP
•
MIT License
•1•1•1•0•Updated Oct 11, 2024Oct 11, 2024
Contributed-MT-leaderboard
Public
Leaderboard of contributed MT results
Makefile
•
Creative Commons Attribution Share Alike 4.0 International
•0•0•0•0•Updated Oct 11, 2024Oct 11, 2024
OPUS-MT-leaderboard-recipes
Public
Makefile recipes shared between all leaderboard repos
Makefile
•
Creative Commons Attribution Share Alike 4.0 International
•0•1•0•0•Updated Oct 10, 2024Oct 10, 2024
sentimentator
Public
Tool for sentiment analysis annotation
HTML
•
MIT License
•6•11•0•0•Updated Oct 8, 2024Oct 8, 2024
lowres-spain-st
Public
This is the repository that contains all scripts and data from the Helsinki-NLP participation to the WMT24 Shared task: Translation into Low-Resource Languages of Spain
Shell
•0•0•0•0•Updated Oct 8, 2024Oct 8, 2024
Opus-MT
Public
Open neural machine translation models and web services
machine-learning natural-language-processing machine-translation neural-machine-translation language-technology language-translation-service translation-service translation-interface
Python
•
MIT License
•71•625•51•0•Updated Oct 7, 2024Oct 7, 2024
dialect-topic-model
Public
Scripts and metadata for the paper "Corpus-based dialectometry with topic models"
Python
•
Creative Commons Attribution 4.0 International
•0•1•0•0•Updated Sep 27, 2024Sep 27, 2024
Tatoeba-Challenge
Public
Makefile
•
Other
•91•807•8•0•Updated Aug 20, 2024Aug 20, 2024
OPUS-MT-train
Public
Training open neural machine translation models
machine-learning natural-language-processing machine-translation language-technology
Makefile
•
MIT License
•41•337•61•1•Updated Aug 16, 2024Aug 16, 2024
OpusFilter
Public
OpusFilter - Parallel corpus processing toolkit
machine-translation parallel-corpus corpus-tools corpus-processing nlp natural-language-processing
Python
•
MIT License
•18•102•6•0•Updated Aug 14, 2024Aug 14, 2024
OpusTools
Public
Python
•18•67•7•2•Updated Aug 8, 2024Aug 8, 2024
opus-fast-mosestokenizer
Public
c++ mosestokenizer (OPUS fork)
C++
•
GNU Lesser General Public License v2.1
•9•3•1•1•Updated Jul 31, 2024Jul 31, 2024
OPUS-MT-testsets
Public
benchmarks for evaluating MT models
Smalltalk
•
Other
•1•11•11•1•Updated Jun 26, 2024Jun 26, 2024
eflomal
Public
Efficient Low-Memory Aligner
C
•
GNU General Public License v3.0
•30•0•0•0•Updated Jun 20, 2024Jun 20, 2024
murre24
Public
Manually annotated dataset of Finnish varieties in the Suomi24, the largest Finnish internet forum, the id's of automatically annotated dialectal messages and the scripts used for classification and evaluation.
Python
•
Creative Commons Attribution 4.0 International
•0•2•0•0•Updated May 21, 2024May 21, 2024
HPLT-MT-leaderboard
Public
Makefile
•
Creative Commons Attribution Share Alike 4.0 International
•0•0•0•0•Updated Apr 11, 2024Apr 11, 2024
OPUS-ingest
Public
Makefile
•0•4•15•0•Updated Mar 20, 2024Mar 20, 2024