Repositories list

• Inforex

  Public
  Inforex is a web system for text corpora construction.

  nlpnatural-language-processingweb-application+ 3annotation-toolannotation-editorannotator-tool

  JavaScript

  •

  Other

  •9•11•1•3•Updated Nov 8, 2024Nov 8, 2024

• PUGG

  Public
  Python

  •0•0•0•0•Updated Aug 12, 2024Aug 12, 2024

• clarin-pl-dspace

  Public
  CLARIN-PL digital library based on DSpace

  Java

  •

  Other

  •1.3k•0•0•1•Updated Jun 13, 2024Jun 13, 2024

• RetNet

  Public
  Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

  Jupyter Notebook

  •

  MIT License

  •24•0•0•0•Updated Apr 2, 2024Apr 2, 2024

• personalized-nlp

  Public
  Jupyter Notebook

  •

  MIT License

  •2•9•1•2•Updated Mar 28, 2024Mar 28, 2024

• chronocorpus

  Public
  Java

  •

  GNU General Public License v3.0

  •1•0•0•7•Updated Feb 8, 2024Feb 8, 2024

• clarin-kontext

  Public
  An advanced, extensible web front-end for the Manatee-open corpus search engine

  TypeScript

  •

  GNU General Public License v2.0

  •22•0•0•0•Updated Dec 14, 2023Dec 14, 2023

• embeddings

  Public
  Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polish Language

  benchmarkclassificationlm+ 5nlp-machine-learningfine-tuninglanguagemodelsequence-taggingnlp

  Python

  •

  MIT License

  •3•36•43•5•Updated Dec 3, 2023Dec 3, 2023

• klajster

  Public
  Python

  •0•0•0•1•Updated Nov 30, 2023Nov 30, 2023

• argilla

  Public
  ✨Argilla: the open-source data curation platform for LLMs

  Python

  •

  Apache License 2.0

  •377•0•0•0•Updated Nov 26, 2023Nov 26, 2023

• LEPISZCZE

  Public
  This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish

  nlpbenchmarkingbenchmark+ 7machine-learningleaderboardnludatasetspolishreproducibilitydvc

  Python

  •

  MIT License

  •2•13•1•1•Updated Nov 24, 2023Nov 24, 2023

• doccano

  Public
  Open source annotation tool for machine learning practitioners.

  Python

  •

  MIT License

  •1.7k•1•0•4•Updated Nov 9, 2023Nov 9, 2023

• personalized-emotion-prediction-with-normalizing-flows

  Public
  0•0•0•0•Updated Oct 14, 2023Oct 14, 2023

• text-augumentation-with-chatgpt

  Public
  Source code for paper "From Big to Small Without Losing It All: Text Augmentation with ChatGPT for Efficient Sentiment Analysis" published at the 13th ICDM Workshop on Sentiment Elicitation from Natural Text for Information Retrieval and Extraction (SENTIRE) organized during the 23rd IEEE International Conference on Data Mining (ICDM 2023)

  Jupyter Notebook

  •0•3•0•0•Updated Oct 12, 2023Oct 12, 2023

• model-based-data-acquisition

  Public
  Source code for paper "Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems" published at the 13th ICDM Workshop on Sentiment Elicitation from Natural Text for Information Retrieval and Extraction (SENTIRE) organized during the 23rd IEEE International Conference on Data Mining (ICDM 2023)

  Jupyter Notebook

  •

  MIT License

  •0•0•0•0•Updated Oct 3, 2023Oct 3, 2023

• capturing-human-perspectives

  Public
  Source code for paper "Capturing Human Perspectives in NLP: Questionnaires, Annotations, and Biases" published at the 2nd Workshop on Perspectivist Approaches to NLP at the 6th European Conference on Artificial Intelligence (NLPerspectives2 @ ECAI 2023)

  Jupyter Notebook

  •

  MIT License

  •1•0•0•0•Updated Sep 17, 2023Sep 17, 2023

• WordNetTextfooler

  Public
  0•0•0•0•Updated Jul 31, 2023Jul 31, 2023

• Liner2

  Public
  Generic framework for information extraction tasks, including recognition of named entities, temporal expressions, spatial expressions and events.

  Java

  •6•12•5•0•Updated Jun 5, 2023Jun 5, 2023

• doccano-client

  Public
  A simple client for doccano API.

  Python

  •

  MIT License

  •62•0•0•0•Updated Apr 13, 2023Apr 13, 2023

• lepiszcze-datatasets-descriptions

  Public
  Temporal storage for LEPISZCZE datasets descriptions

  0•0•0•0•Updated Mar 29, 2023Mar 29, 2023

• PolDeepSpatial

  Public
  A tool for recognition of spatial expressions containing trajector, spatial indicator and landmark.

  Python

  •0•0•0•1•Updated Mar 24, 2023Mar 24, 2023

• PolDeepNer

  Public
  Tool for named entity recognition for Polish based on deep learning.

  Python

  •6•29•1•1•Updated Mar 24, 2023Mar 24, 2023

• chatgpt-evaluation-01-2023

  Public
  Code, datasets and results of the ChatGPT evaluation presented in paper "ChatGPT: Jack of all trades, master of none"

  Jupyter Notebook

  •

  MIT License

  •4•29•0•0•Updated Mar 7, 2023Mar 7, 2023

• polonjid-dictionary-angular

  Public
  Single page application, angular (http://polonjid-dictionary.clarin-pl.eu)

  TypeScript

  •

  GNU General Public License v3.0

  •0•0•0•7•Updated Feb 4, 2023Feb 4, 2023

• SPF-SPs-metadata

  Public
  Metadata sources for all service providers in the CLARIN Service Provider Federation

  Shell

  •58•0•0•0•Updated Jan 5, 2023Jan 5, 2023

• Polem

  Public
  Tool for lemmatization of multi-word phrases and named entities for Polish.

  HTML

  •

  GNU Lesser General Public License v3.0

  •4•8•1•0•Updated Dec 6, 2022Dec 6, 2022

• wordnetloom

  Public
  Wordnet Visual Editor

  Java

  •

  Other

  •1•1•0•4•Updated Nov 24, 2022Nov 24, 2022

• mwe-vector-methods

  Public
  Multiword expressions detection methods based on the vector representations

  Jupyter Notebook

  •

  MIT License

  •1•0•0•1•Updated Nov 2, 2022Nov 2, 2022

• speech-annotationpro-plugin

  Public
  Annotation Pro plugin utilizing ClarinPL speech tools and models

  C++

  •

  MIT License

  •0•3•0•0•Updated Oct 12, 2022Oct 12, 2022

• abusive-clauses-dashboard

  Public
  MIT License

  •0•0•0•2•Updated Sep 23, 2022Sep 23, 2022