Skip to content
Change the repository type filter

All

    Repositories list

    • TrMor2018

      Public
      Turkish Morphology Datasets
      Perl
      MIT License
      13400Updated Sep 25, 2023Sep 25, 2023
    • Morse.jl

      Public
      Paper: Morphological Analysis Using a Sequence Decoder
      Julia
      MIT License
      61451Updated Aug 8, 2021Aug 8, 2021
    • Paradigmatic approach to Childes child data.
      Max
      4000Updated May 26, 2018May 26, 2018
    • wvec

      Public
      Word vectors
      Perl
      MIT License
      126410Updated May 26, 2018May 26, 2018
    • trmor

      Public
      Turkish morphological analyzer
      Perl
      0000Updated Aug 3, 2017Aug 3, 2017
    • fda

      Public
      Feature Decay Algorithm
      C
      Other
      0400Updated Dec 2, 2015Dec 2, 2015
    • fastsubs

      Public
      Generate most likely substitutes for words in a given text based on an n-gram language model.
      C
      Other
      31000Updated Apr 15, 2015Apr 15, 2015
    • wkmeans

      Public
      k-means algorithm with (optional) instance weights.
      C
      MIT License
      11510Updated Mar 7, 2015Mar 7, 2015
    • uwsd

      Public
      Unsupervised word sense disambiguation
      Python
      MIT License
      0200Updated Aug 28, 2014Aug 28, 2014
    • tr-en-edu

      Public
      C++
      10700Updated Jul 2, 2014Jul 2, 2014
    • upos_2014

      Public
      Unsupervised multilingual part of speech induction system (2014 version)
      TeX
      MIT License
      0510Updated Jun 24, 2014Jun 24, 2014
    • scode

      Public
      Sphere embedding (s-code) is a variation of Euclidean embedding of co-occurence data (code).
      C
      MIT License
      1410Updated May 9, 2014May 9, 2014
    • langvis

      Public
      Java
      MIT License
      0000Updated Mar 26, 2014Mar 26, 2014
    • Supporting code and data for the langvis project.
      C
      MIT License
      0000Updated Mar 24, 2014Mar 24, 2014
    • protein

      Public
      Protein dynamics research.
      C
      0110Updated Feb 12, 2014Feb 12, 2014
    • glookup

      Public
      glookup - reads ngram patterns with wildcards from stdin and prints their counts from the Web1T Google ngram data.
      Perl
      0000Updated Jan 14, 2014Jan 14, 2014
    • Demo run of the S-CODE algorithm on a 3D-Sphere
      MIT License
      0000Updated Jan 13, 2014Jan 13, 2014
    • dist

      Public
      Calculates a variety of distances between vectors.
      C
      MIT License
      0300Updated Jan 13, 2014Jan 13, 2014
    • Semeval 2013 | Task 13 WSI and WSD
      Java
      4200Updated Jan 12, 2014Jan 12, 2014
    • lsdbc

      Public
      C
      Other
      1300Updated Jan 9, 2014Jan 9, 2014
    • bestLM

      Public
      Run SRILM with different options to find the best language model given the training and test data.
      Perl
      MIT License
      1100Updated Nov 16, 2013Nov 16, 2013
    • usense

      Public
      Word Sense Induction
      C
      2000Updated Jul 30, 2013Jul 30, 2013
    • upos

      Public
      Unsupervised part of speech induction.
      JavaScript
      MIT License
      1300Updated Jul 4, 2013Jul 4, 2013
    • CONNL-X Turkish data set of upos repository
      0100Updated Apr 8, 2013Apr 8, 2013
    • CONNL-X Spanish data set of upos repository
      0000Updated Apr 8, 2013Apr 8, 2013
    • CONNL-X Swedish data set of upos repository
      0000Updated Apr 8, 2013Apr 8, 2013
    • CONNL-X Slovene data set of upos repository
      0000Updated Apr 8, 2013Apr 8, 2013
    • CONNL-X German data set of upos repository
      0000Updated Apr 8, 2013Apr 8, 2013
    • CONNL-X Portuguese data set of upos repository
      0000Updated Apr 8, 2013Apr 8, 2013
    • CONNL-X Dutch data set of upos repository
      0000Updated Apr 8, 2013Apr 8, 2013