Skip to content

@transducens Transducens

Change the repository type filter

All

    Repositories list

    40 repositories

    • demint

      Public
      Repository for the project "DeMINT: Automated Language Debriefing for English Learners via AI Chatbot Analysis of Meeting Transcripts"
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Oct 25, 2024Oct 25, 2024

    • PILAR

      Public
      Creative Commons Zero v1.0 Universal
      •0•3•0•0•Updated Oct 23, 2024Oct 23, 2024

    • trad-automatica-neuronal-valenciano

      Public
      JavaScript
      •
      GNU General Public License v3.0
      •0•0•0•0•Updated Oct 8, 2024Oct 8, 2024

    • elrd

      Public
      Home of the English Learners Role-Playing Dialogue Dataset (ELRD).
      Other
      •0•0•0•0•Updated Oct 7, 2024Oct 7, 2024

    • transducens-website

      Public
      Markdown and static files for the Transducens research group's website.
      HTML
      •0•0•0•0•Updated Jul 30, 2024Jul 30, 2024

    • wmt2024-romance-tests

      Public
      Repository containing the test files for the WMT24 Shared Task: Translation into Low-Resource Languages of Spain
      0•0•0•0•Updated Jul 23, 2024Jul 23, 2024

    • mayanv

      Public
      Hosts a number of bilingual Mayan-Spanish corpora
      JavaScript
      •
      Creative Commons Zero v1.0 Universal
      •1•5•0•0•Updated Jun 16, 2024Jun 16, 2024

    • compiladores

      Public
      Código fuente del libro "Diseño de compiladores"
      TeX
      •
      Apache License 2.0
      •0•1•0•0•Updated Apr 29, 2024Apr 29, 2024

    • idiomata_cognitor

      Public
      Language identifier for Romance languages
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Apr 25, 2024Apr 25, 2024

    • nmt-maya

      Public
      Hosts code to train bilingual and multilingual NMT models of Mayan languages
      JavaScript
      •0•0•0•0•Updated Mar 22, 2024Mar 22, 2024

    • parallel-urls-classifier

      Public
      Parallel URLs Classifier (PUC) infers the parallelness of a pair of documents from their URLs
      urlcrawlingdocument-aligner
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Mar 18, 2024Mar 18, 2024

    • url2lang

      Public
      url2lang infers the language of a document from its URL
      urlcrawlinglanguage-identification
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Mar 15, 2024Mar 15, 2024

    • linguacrawl

      Public
      Crawling engine that crawls a set of top-level domains looking for documents in a list of languages
      Python
      •
      GNU General Public License v3.0
      •3•11•2•3•Updated Feb 6, 2024Feb 6, 2024

    • jw_crawler

      Public
      Python
      •0•0•0•0•Updated Jan 11, 2024Jan 11, 2024

    • MaTiLDA

      Public
      Python
      •
      GNU General Public License v3.0
      •0•0•0•0•Updated Nov 28, 2023Nov 28, 2023

    • mtl-da-emnlp

      Public
      Code to reproduce the experiments presented in the EMNLP 2021 paper "Rethinking data augmentation for low-resource neural machine translation: a multi-task learning approach"
      Shell
      •2•5•1•0•Updated Nov 28, 2023Nov 28, 2023

    • CrossLingualNeuralFMS

      Public
      Code to reproduce the experiments reported in the paper "Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation" published in EMNLP 2022
      Java
      •
      GNU General Public License v3.0
      •0•1•0•0•Updated Dec 9, 2022Dec 9, 2022

    • tune-n-distill

      Public
      Exploiting large pre-trained models for low-resource neural machine translation
      Shell
      •0•0•0•0•Updated Jun 30, 2022Jun 30, 2022

    • biwords

      Public
      Processing of word alignments for compressing parallel corpora
      C++
      •
      GNU General Public License v2.0
      •0•0•0•0•Updated Oct 21, 2021Oct 21, 2021

    • bitext2bilexicon

      Public
      Tool that allows to build a bilingual lexicon from a parallel corpus
      Shell
      •0•0•0•0•Updated Aug 31, 2021Aug 31, 2021

    • python-Levenshtein

      Public
      The Levenshtein Python C extension module contains functions for fast computation of Levenshtein distance and string similarity
      C
      •
      GNU General Public License v2.0
      •229•0•0•0•Updated Aug 11, 2021Aug 11, 2021

    • bayeseq

      Public
      Auto-encoding variational Bayesian inference for sequence generation models.
      Python
      •
      MIT License
      •10•0•0•0•Updated Jan 20, 2021Jan 20, 2021

    • smart-segmentation

      Public
      Shell
      •
      GNU General Public License v3.0
      •0•2•0•0•Updated Oct 12, 2020Oct 12, 2020

    • OmegaT-FuzzyMatchRepair-Plugin

      Public
      Java
      •
      GNU General Public License v3.0
      •2•0•1•0•Updated May 4, 2020May 4, 2020

    • gourmet-ua

      Public
      Developments of UA for the EU project GoURMET
      Python
      •1•1•0•0•Updated Feb 3, 2020Feb 3, 2020

    • JSONL2bitextor

      Public
      Script and instructions to produce a Bitextor-compatible parallel-data-extraction task from JSONL files as provided by BBC
      Python
      •0•1•0•0•Updated Dec 20, 2019Dec 20, 2019

    • LASERtrain

      Public
      Python
      •5•21•2•0•Updated Dec 20, 2019Dec 20, 2019

    • LASER

      Public
      Language-Agnostic SEntence Representations
      Python
      •
      Other
      •463•0•0•0•Updated Jun 26, 2019Jun 26, 2019

    • Forecat-OmegaT

      Public
      Plugin that adds the functionality of Forecat (https://github.com/jaspock/forecat) to OmegaT.
      Java
      •
      GNU General Public License v3.0
      •0•8•7•0•Updated Jun 12, 2018Jun 12, 2018

    • forecat

      Public
      Java
      •
      GNU Affero General Public License v3.0
      •1•8•0•0•Updated Aug 22, 2017Aug 22, 2017