HOSemiCRF
High-order Semi-Markov Conditional Random Field
Install / Use
/learn @nvcuong/HOSemiCRFREADME
Source code for High-order Semi-Markov Conditional Random Field model
=== WARNING ===
HOSemiCRF requires a lot of memory usage. It is best to run the program in parallel on a computing cluster with lots of memory.
=== COMPILATION STEPS ===
Requirement: Apache Ant (http://ant.apache.org/)
-
Download the HOSemiCRF repository as a zip file: HOSemiCRF-master.zip
-
Unzip the file:
unzip HOSemiCRF-master.zip
-
Compile the program:
cd HOSemiCRF-master
ant
=== RUN THE PUNCTUATION PREDICTION PROGRAM ===
cp dist/lib/HOSemiCRF.jar run/punc/
cd run/punc
java -cp "HOSemiCRF.jar" Applications.PunctuationPredictor all punc.conf
=== RUN THE REFERENCE PREDICTION PROGRAM ===
cp dist/lib/HOSemiCRF.jar run/ref/
cd run/ref
java -cp "HOSemiCRF.jar" Applications.ReferenceTagger all ref.conf
=== RUN THE OCR PROGRAM ===
Download data from http://www.seas.upenn.edu/~taskar/ocr/ to the folder run/ocr/
cp dist/lib/HOSemiCRF.jar run/ocr/
cd run/ocr
java -cp "HOSemiCRF.jar" OCR.OCR all ocr.conf 0
=== MORE INFO ===
Please visit: https://github.com/nvcuong/HOSemiCRF/wiki
Related Skills
node-connect
339.5kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
83.9kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
339.5kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
commit-push-pr
83.9kCommit, push, and open a PR
