cld3-cli

A command-line interface for Google's CLD3 language identification model.

spm_filter

A tool for filtering segments which are too long or too short after being encoded with a sentencepiece model

human-or-neural-translation-demo

A small repro of the "Human or Neural Translation?" paper by Bhardwaj et al.

mecab-ko-dic

erip

My silly little page

wsd-with-salient-context

Code accompanying "Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context"

ling473-proj4

Project Four -- DNA Sequence Searching

ling473-proj3

Project Three -- Thai Syllabic Segmentation