Skip to content

@UppsalaNLP The Uppsala NLP group

Change the repository type filter

All

    Repositories list

    13 repositories

    • Spoken-ImplicitDR

      Public
      Dataset for the COLING2025 paper “Multimodal Extraction and Recognition of Arabic Implicit Discourse Relations.”
      implicitprosodymultimodaldiscourse-relation-recognition
      1•0•0•0•Updated Jan 21, 2025Jan 21, 2025

    • UD-MULTIGENRE

      Public
      UD-based dataset enriched with genre annotations
      Python
      •
      Other
      •0•0•0•0•Updated Jul 26, 2024Jul 26, 2024

    • genre_topic_transfer

      Public
      Notebooks and data for the paper "Relation between Cross-Genre and Cross-Topic Transfer in Dependency Parsing" by Vera Danilova and Sara Stymne (to be published at LREC-COLING 2024)
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Mar 24, 2024Mar 24, 2024

    • LitDialogSilver

      Public
      Literary works automatically annotated with speech segments and speech tags based on quotation marks and heuristics.
      0•0•0•0•Updated Mar 18, 2024Mar 18, 2024

    • SweSubEval

      Public
      Evaluation data for subordinate clauses from Swedish literary text from 1800–1930
      0•0•0•0•Updated May 3, 2023May 3, 2023

    • causality_demo

      Public
      Python
      •0•0•0•0•Updated Dec 5, 2022Dec 5, 2022

    • uuparser

      Public
      A transition-based parser for Universal Dependencies with BiLSTM word and character representations.
      Python
      •
      Apache License 2.0
      •25•80•10•1•Updated Jun 21, 2022Jun 21, 2022

    • SOU-corpus

      Public
      HTML
      •0•2•0•0•Updated Jun 16, 2022Jun 16, 2022

    • Swedish-Causality-Datasets

      Public
      Creative Commons Attribution 4.0 International
      •0•2•0•0•Updated Jun 16, 2022Jun 16, 2022

    • principal_word_vectors

      Public
      We use principal component analysis for word embedding. The method is able to process both annotated and raw corpora.
      C
      •2•0•0•0•Updated Apr 28, 2019Apr 28, 2019

    • uuPronPred

      Public
      System for cross-lingual pronoun prediction, based on BiLSTMs.
      Python
      •0•3•0•0•Updated Dec 3, 2017Dec 3, 2017

    • segmenter

      Public
      Universal segmenter based on the Universal Dependency framework, written by Y. Shao, Uppsala University
      Python
      •15•5•0•0•Updated Sep 4, 2017Sep 4, 2017

    • tagger

      Public
      A Joint Chinese segmentation and POS tagger based on bidirectional GRU-CRF
      Python
      •44•1•0•0•Updated May 10, 2017May 10, 2017