jhnwnstd

MA in Linguistics with a specialization in character-level language modeling.

Pinned Repositories

corpus_toolkit
Python toolkit for corpus analysis: tokenization, lexical diversity, vocabulary growth prediction, entropy measures, and Zipf/Heaps visualizations.
Language:Python6 1 00
hayes2009
Hayes 2009 phonological feature tables
Language:Python1 0 00
linguist_toolkit
Python and coding tools for collecting text and audio data.
Language:Python10 1 00
morpheme_segmenter
python code that segements words into morphemes based on statistical properties of a corpus.
Language:Python1 1 00
MorphoLex-en
Lexical database for ~70k English words with morphological variables
Language:Python1 0 00
shannon
This project uses KenLM to analyze language entropy and redundancy in English and Linear B.
Language:Python2 1 00
suxotin
Python script that distinguishes vowels from consonants using Suxotin's algorithm.
Language:Python2 1 00
syllabify
Python module for syllabifying English ARPABET transcriptions
Language:Python1 0 00
thesis
Contains the code from my thesis project.
Language:Python0 0 00
writing_direction
This script predicts language directionality (LTR or RTL) using Gini and entropy calculations on character distributions from Europarl and UDHR corpora.
Language:Python1 1 00

jhnwnstd/linguist_toolkit
Python and coding tools for collecting text and audio data.
Language:Python10 1 00
jhnwnstd/corpus_toolkit
Python toolkit for corpus analysis: tokenization, lexical diversity, vocabulary growth prediction, entropy measures, and Zipf/Heaps visualizations.
Language:Python6 1 00
jhnwnstd/shannon
This project uses KenLM to analyze language entropy and redundancy in English and Linear B.
Language:Python2 1 00
jhnwnstd/suxotin
Python script that distinguishes vowels from consonants using Suxotin's algorithm.
Language:Python2 1 00
jhnwnstd/hayes2009
Hayes 2009 phonological feature tables
Language:Python1 0 00
jhnwnstd/morpheme_segmenter
python code that segements words into morphemes based on statistical properties of a corpus.
Language:Python1 1 00
jhnwnstd/MorphoLex-en
Lexical database for ~70k English words with morphological variables
Language:Python1 0 00
jhnwnstd/syllabify
Python module for syllabifying English ARPABET transcriptions
Language:Python1 0 00
jhnwnstd/writing_direction
This script predicts language directionality (LTR or RTL) using Gini and entropy calculations on character distributions from Europarl and UDHR corpora.
Language:Python1 1 00
jhnwnstd/thesis
Contains the code from my thesis project.
Language:Python0 0 00