clmarr Goto Github PK

albanian-cfr

In progress: computerized forward reconstruction applied to Albanian, using DiaSim. Currently building cascades and revising lexicon files. Currently only working on the ancient Latin loan layer -- ultimately hope to expand to other layers.

clmarrcs203final

bank application as for final

clmarrthesis

My undergraduate thesis, in culmination and completion of an Independent Major at Vassar College

comp-sem-suret-toyset

diasim

Work in progress: A Java-written architecture, built using modern phonology theory in the Neogrammarian tradition, which can be used to simulate the realization of diachronic sound change, given the starting phonological forms for the lexemes and an ordered list of historical rules. Undergoing renovation but current form should run as of 12/22/2022

geez-cfr

Toy reconstruction for Ge'ez from Proto-West-Semitic

herodotos-beta

Exploratory work with NER tagging of other texts for downstream purposes.

herodotos-cltk

The Classical Language Toolkit modified for the Herodotos-beta project

irish-toy-cfr

languagemodel

languagemodelproject

modern-south-arabian-cfr

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

rukaten_asmt

experiment with using Jupyter Notebooks for demonstrating my ML pipeline improv procedures

tangkhulic-cfr

word-embeddings-for-nmt

Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018

xnmt

eXtensible Neural Machine Translation