Robert Pugh's repositories
nahuatl-variant-charlms-americasnlp
Code for our AmericasNLP Workshop paper "Investigating variation in written forms of Nahuatl using character-based language models"
fst-nahuatl
Using Finite-State Transducers to model Western Sierra Nahuatl morphology and orthography.
nahuatl-orthography
grapheme-to-phoneme and phoneme-to-grapheme in Nahuatl. Supports variable input orthography
arborator-frontend
VueJs based user interface for Arborator-flask
common-voice
Common Voice is part of Mozilla's initiative to help teach machines how real people speak.
docs
Universal Dependencies online documentation
en-es-codeswitching-ud-treebank
UD treebank for a Spanish-English codeswitching corpus (Miami BangorTalk corpus)
fst-morph-ncx
Analizador morfológico para el náhuatl del centro de Puebla (iso 639-3: ncx)
hbo-UD
conversion of ETCBC Old Testament data to UD
lexical-models
Lexical language models for predictive text
LING-L645
Practical repository for LING L-645
machamp
Repository with code for MaChAmp: https://aclanthology.org/2021.eacl-demos.22/
mesokey
Writing tools for Mesoamerican languages
plain-academic
A truly simple website template for academics
pytorch-tutorials
PyTorch tutorials.
udapi-python
Python framework for processing Universal Dependencies data
udify
A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.