Skip to content

@TurkuNLP TurkuNLP Group - IT Department - University of Turku

Change the repository type filter

All

    Repositories list

    128 repositories

    • LLM_document_descriptors

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Jan 18, 2025Jan 18, 2025

    • finerweb-10bt

      Public
      Code for FinerWeb-10BT – tools for cleaning web data line by line using LLMs
      Python
      •
      MIT License
      •1•0•0•0•Updated Jan 16, 2025Jan 16, 2025

    • ECCO-ocr-large-run

      Public
      Code for the large LUMI run of ECCO ocr correction
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Jan 16, 2025Jan 16, 2025

    • DIKI1002-Working-with-Text-in-Python

      Public
      0•4•0•0•Updated Jan 14, 2025Jan 14, 2025

    • Keyword-embeddings-clusters

      Public
      Clusters with keywords grouped based on their word embeddings
      0•0•0•0•Updated Jan 14, 2025Jan 14, 2025

    • list-of-publications

      Public
      Turku NLP list of publications
      TeX
      •2•0•0•0•Updated Jan 14, 2025Jan 14, 2025

    • textual-data-analysis-course

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •0•3•0•0•Updated Jan 13, 2025Jan 13, 2025

    • pytorch-registerlabeling

      Public
      Python
      •1•1•0•0•Updated Jan 1, 2025Jan 1, 2025

    • turkunlp.github.io

      Public
      A Jekyll version of the "Editorial" theme by HTML5 UP.
      JavaScript
      •
      Other
      •150•2•0•0•Updated Dec 19, 2024Dec 19, 2024

    • htr-table-pipeline

      Public
      Handwritten text recognition pipeline for table data
      Jupyter Notebook
      •
      Apache License 2.0
      •0•0•0•0•Updated Dec 19, 2024Dec 19, 2024

    • htr-annotations

      Public
      Handwritten text recognition annotations
      0•0•0•0•Updated Dec 16, 2024Dec 16, 2024

    • ocr-postcorrection-lm

      Public
      Code to try out ocr postcorrection with language models
      Jupyter Notebook
      •0•0•1•0•Updated Dec 16, 2024Dec 16, 2024

    • ATP_kurssi

      Public
      Jupyter Notebook
      •4•4•0•0•Updated Dec 9, 2024Dec 9, 2024

    • RAG-web-app

      Public
      HTML
      •0•3•6•0•Updated Dec 3, 2024Dec 3, 2024

    • ecco-ocr-ec

      Public
      Python
      •0•0•0•0•Updated Nov 28, 2024Nov 28, 2024

    • vLLM-recipes

      Public
      Different vLLM setups on different machines
      Python
      •0•0•0•0•Updated Nov 15, 2024Nov 15, 2024

    • Deep_Learning_in_LangTech_course

      Public
      Materials for the University of Turku course TKO_8965 Deep Learning in Human Language Technology (previously named TKO_2101 Natural Language Processing)
      Jupyter Notebook
      •
      Other
      •11•19•0•0•Updated Oct 15, 2024Oct 15, 2024

    • ocr_errors_simulator

      Public
      Functions and codes used to determine probabilities on OCR errors and simulate them
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Oct 10, 2024Oct 10, 2024

    • situational-analysis-llm

      Public
      Code and data for multilingual situational analysis of web registers using LLMs.
      Apache License 2.0
      •0•0•0•0•Updated Oct 4, 2024Oct 4, 2024

    • TurCORE

      Public
      Turkish Corpus of Online REgisters (TurCORE)
      0•0•0•0•Updated Oct 3, 2024Oct 3, 2024

    • intro-to-nlp

      Public
      Introduction to Natural Language Processing
      Jupyter Notebook
      •
      Other
      •26•5•0•0•Updated Sep 17, 2024Sep 17, 2024

    • multilingual-CORE

      Public
      0•0•0•0•Updated Sep 4, 2024Sep 4, 2024

    • Karelia-Project

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •0•1•0•0•Updated Aug 8, 2024Aug 8, 2024

    • register-qa

      Public
      Jupyter Notebook
      •0•0•0•0•Updated May 28, 2024May 28, 2024

    • lumi-nlp-recipes

      Public
      Python
      •2•3•0•0•Updated May 10, 2024May 10, 2024

    • Turku-neural-parser-pipeline

      Public
      A neural parsing pipeline for segmentation, morphological tagging, dependency parsing and lemmatization with pre-trained models for more than 50 languages. Top ranker in the CoNLL-18 Shared Task.
      Python
      •
      Apache License 2.0
      •31•112•11•0•Updated May 7, 2024May 7, 2024

    • DIKI1003-NLP-for-Linguists

      Public
      0•2•0•0•Updated May 2, 2024May 2, 2024

    • Open-Assistant

      Public
      Data collection for Finnish language using OpenAssistant-platform
      Python
      •
      Apache License 2.0
      •3.3k•0•6•0•Updated Mar 27, 2024Mar 27, 2024

    • toxicity-classifier

      Public
      Repository for all things related to classifying whether a text is toxic or not using data from https://github.com/TurkuNLP/wikipedia-toxicity-data-fi
      deep-learningtext-classificationpytorch
      Python
      •0•2•0•0•Updated Mar 7, 2024Mar 7, 2024

    • FinParl-emotion

      Public
      Emotion analysis for Finnish parliamentary speeches
      Jupyter Notebook
      •0•2•0•0•Updated Feb 26, 2024Feb 26, 2024