So Miyagawa's repositories
converter-complex-python
Encode text from legacy ASCII font by Van Damme & Wurst to UTF-8
deipnosophistae-reuses
Citable analyses of quotations and text reuses in the Deipnosophistae
homeric-reuse
Citable analyses of Homeric text reuse in the Deipnosophistae
ANNIS
ANNIS is an open source, versatile web browser-based search and visualization architecture for complex multilevel linguistic corpora with diverse types of annotation.
canonical-greekLit
XML Canonical resources for Greek Literature
coptic-xml-tool
coptic scriptorium xml editor tool
corpora-legacy-releases
Corpora-Legacy-Releases
isri-ocr-evaluation-tools
Automatically exported from code.google.com/p/isri-ocr-evaluation-tools
KR6a0005
佛般泥洹經-西晉-白法祖
lexical-taggers
lexical taggers (language of origin, lemmatizer) for Sahidic Coptic
mozc
Mozc - a Japanese Input Method Editor designed for multi-platform
normalizer
Normalizes orthography
ocropy
Python-based tools for document analysis and OCR
PoCoTo
Home of the Postcorrection Tool
SunoikisisDC-2016
Planning Seminar and SS 2016 Course
tesseract
Tesseract Open Source OCR Engine (main repository)
TheoryOfComputation
A memo of a lecture on Theory of Computation in the University of Tokyo.
tokenizers
Coptic SCRIPTORIUM Tokenization Script
treebank_data
Perseus Treebank Data
WebAlgo-Java-Class
Because most of the code I write is closed source and I wanted to give others a peek into my Java world. So, I have available, upon request, source code and documentation from a Web Algorithms class, part of a Java Certification track at UCB, done while I was independently learning Java. Granted it is probably not up to what I do today but it is at least something for people to look at should they feel the need to know that I have Java experience. During the class I wrote things as diverse as a grails gwt mashup plugin for Eclipse, all the way to a lingpipe, lucene based document classifier, and grammar processor for word separation in Coptic. The classifier (K-Means) and processor was capable of Coptic word splitting with high accuracy armed with very little training data and could distinguish between poetry, religious text and business documents.