Skip to content

@UBC-NLP UBC Deep Learning & NLP Group

Change the repository type filter

All

    Repositories list

    64 repositories

    • InterPARES_audio

      Public
      InterPARES-Audio is an automated, end-to-end pipeline that transforms complex, lengthy audio files into structured, insightful text
      Jupyter Notebook
      •0•1•0•0•Updated Dec 8, 2025Dec 8, 2025

    • InterPARES_chat

      Public
      An AI-powered conversational assistant designed to help users explore and understand InterPARES (International Research on Permanent Authentic Records in Electronic Systems) documents through natural language queries.
      Python
      •0•0•0•0•Updated Dec 4, 2025Dec 4, 2025

    • InterPARES_vision

      Public
      InterPARES-Vision is an advanced OCR (Optical Character Recognition) and layout analysis tool designed specifically for archival documents. It combines state-of-the-art AI vision models to extract text, preserve document structure, and generate machine-readable outputs from scanned documents and images.
      Python
      •0•0•0•0•Updated Dec 4, 2025Dec 4, 2025

    • nilechat

      Public
      2•7•0•0•Updated Nov 11, 2025Nov 11, 2025

    • palmx_2025

      Public
      This repository contains the evaluation code and data for the PalmX 2025 Shared Task on Benchmarking LLMs for Arabic and Islamic Culture.
      Python
      •1•1•0•0•Updated Sep 3, 2025Sep 3, 2025

    • Toucan

      Public
      1•6•0•0•Updated Sep 2, 2025Sep 2, 2025

    • sahara

      Public
      Benchmarking African NLP
      Python
      •0•1•0•0•Updated Aug 18, 2025Aug 18, 2025

    • palm

      Public
      Python
      •6•31•0•0•Updated Aug 8, 2025Aug 8, 2025

    • pearl

      Public
      An official repository for the paper “Pearl: A Multimodal, Culturally-Aware Arabic Instruction Dataset.”
      Python
      •0•5•0•0•Updated May 29, 2025May 29, 2025

    • afrolid

      Public
      AfroLID, a powerful neural toolkit for African languages identification which covers 517 African languages.
      nlpdeep-learningtoolkitafrican-languageslanguage-identificationubc-nlpnatural-langauge-processingdlnlp
      Python
      •
      Apache License 2.0
      •10•34•1•1•Updated Mar 10, 2025Mar 10, 2025

    • COLX_565_sentiment_instructors

      Public
      0•0•0•0•Updated Mar 4, 2025Mar 4, 2025

    • uDistilWhisper

      Public
      uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes ( NAACL'2025 )
      Python
      •
      MIT License
      •0•2•1•0•Updated Feb 11, 2025Feb 11, 2025

    • SPARROW

      Public
      EMNLP 2023
      0•3•0•0•Updated Feb 7, 2025Feb 7, 2025

    • peacock

      Public
      This is the official repository for Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks.
      2•26•1•0•Updated Dec 9, 2024Dec 9, 2024

    • arastories

      Public
      Jupyter Notebook
      •1•9•1•0•Updated Oct 10, 2024Oct 10, 2024

    • VioletV2

      Public
      Python
      •
      MIT License
      •0•0•0•0•Updated Sep 11, 2024Sep 11, 2024

    • Cheetah

      Public
      2•4•0•0•Updated Aug 12, 2024Aug 12, 2024

    • MoS

      Public
      Python
      •
      GNU General Public License v3.0
      •0•0•0•0•Updated Aug 7, 2024Aug 7, 2024

    • llmas

      Public
      Python
      •
      Other
      •0•3•0•0•Updated Aug 7, 2024Aug 7, 2024

    • copticmt

      Public
      Python
      •0•0•0•0•Updated Jul 7, 2024Jul 7, 2024

    • Babel-670-Language-Identification

      Public
      A repo for Fumbling in Babel paper at NAACL2024: https://aclanthology.org/2024.findings-naacl.274/
      0•0•0•0•Updated Jul 5, 2024Jul 5, 2024

    • AraNet

      Public
      Python
      •
      GNU General Public License v3.0
      •8•21•0•4•Updated Jun 15, 2024Jun 15, 2024

    • casablanca.github.io

      Public
      HTML
      •
      MIT License
      •0•0•0•0•Updated Jun 11, 2024Jun 11, 2024

    • fintral

      Public
      0•8•1•0•Updated Jun 5, 2024Jun 5, 2024

    • araT5

      Public
      AraT5: Text-to-Text Transformers for Arabic Language Understanding
      qamachine-translationtransformergenerationsummarizationarabicarabic-nlpparaphraset5t5-model
      24•93•11•1•Updated May 16, 2024May 16, 2024

    • octopus

      Public
      Octopus is a neural machine generation toolkit for Arabic Natural Lnagauge Generation (NLG)
      paraphrasesummarizeanswer-questiongenerate-questionarabic-nlgdiacritizecorrect-grammargenerate-titletranslitrate
      Python
      •1•9•1•0•Updated Apr 29, 2024Apr 29, 2024

    • nadi

      Public
      Nuanced Arabic Dialect Identification Shared Tasks (NADI) 2020 and 2021
      ubcarabicarabic-nlparabic-dialectsnadi2020nadi2021ubc-nlp-lab
      Python
      •2•5•0•0•Updated Mar 4, 2024Mar 4, 2024

    • ItrustAI_RP06

      Public
      Repo for Project RP06 at I Trust AI project
      0•0•0•0•Updated Feb 7, 2024Feb 7, 2024

    • orca

      Public
      ORCA is a large-scale Arabic Language Understanding Evaluation Benchmark
      Python
      •
      Apache License 2.0
      •3•8•2•0•Updated Oct 30, 2023Oct 30, 2023

    • serengeti

      Public
      SERENGETI: Massively Multilingual Language Models for Africa
      Jupyter Notebook
      •
      Apache License 2.0
      •2•17•1•0•Updated Oct 26, 2023Oct 26, 2023