Pinned Repositories
wikipron
Massively multilingual pronunciation mining
BP-truncation
Modeling word truncation in Brazilian Portuguese
iso639
ISO 639 language codes
lxa5
Linguistica 5: Unsupervised Learning of Linguistic Structure
nskipgrams
A lightweight Python package to work with ngrams and skipgrams
pycantonese
Cantonese Linguistics and NLP
pylangacq
Language Acquisition Research Tools
uchicago-beamer
LaTeX beamer theme for University of Chicago-themed presentation slides
wikipron
Scraping grapheme-to-phoneme data from Wiktionary
wordseg
Word segmentation models
jacksonllee's Repositories
jacksonllee/pycantonese
Cantonese Linguistics and NLP
jacksonllee/pylangacq
Language Acquisition Research Tools
jacksonllee/iso639
ISO 639 language codes
jacksonllee/uchicago-beamer
LaTeX beamer theme for University of Chicago-themed presentation slides
jacksonllee/nskipgrams
A lightweight Python package to work with ngrams and skipgrams
jacksonllee/wikipron
Scraping grapheme-to-phoneme data from Wiktionary
jacksonllee/BP-truncation
Modeling word truncation in Brazilian Portuguese
jacksonllee/wordseg
Word segmentation models
jacksonllee/lxa5
Linguistica 5: Unsupervised Learning of Linguistic Structure
jacksonllee/morph-align-cluster
Automatic morphological alignment and clustering
jacksonllee/parse-jyutping
Parsing Cantonese Jyutping romanization in Python
jacksonllee/chao1930
A system of "tone-letters" (Chao 1930)
jacksonllee/datasets
Datasets for linguistic research
jacksonllee/recipes
Ingredients for my machines and projects #yummm (dotfiles, set-up notes, project templates, etc.)
jacksonllee/stem-extract
Inflectional stem identification
jacksonllee/cls-proceedings
Python-based command line tool for compiling the proceedings of the Chicago Linguistic Society (CLS)
jacksonllee/multi-tiered-cantonese-word-segmentation
jacksonllee/python-library-template
Because I work on a new(-ish) Python library every quarter or so
jacksonllee/rime-cantonese
Rime Cantonese input schema | 粵語拼音輸入方案
jacksonllee/successor-predecessor-freq
Projects using successor and predecessor frequencies