Christos Christodoulopoulos

Bible Corpus
A multilingual parallel corpus containing 100 translations of the Bible.

Older resources - kept for historical preservation:

StatOpenCCG parser
A statistical generative parser for CCG.
Syntactic tree viewer
A collapsable/zoomable tree viewer for bracketed (PTB- and CCG-style) syntactic trees.
Android notification for Java/Bash
A solution for sending push notifications from Java code or Bash scripts to Android devices.
Edison
A powerful NLP feature extraction library based on the CogComp data structures.
Open-Eval
An open-source web-based ML/NLP evaluation tool that uses the CogComp data structures.
Jubilee
An extension of the original Jubilee project which includes tree-editing, annotation insertions/deletions and a JSON-based file format.
Used in the extended BabySRL annotation project.
Comma SRL
An LBJava classifier for identifying comma relations (with Naveen Arivazhagan).
Twitter Sentiment Classifier
An LBJava sentiment classifier for the Twitter firehose (including a twitter client, based on Hosebird).
BMMM: Bayesian Multinomial Mixture Model
An unsupervised PoS inducer.
PoS Induction evaluation scripts
Evaluation of an unsupervised PoS induction system over many-to-1, 1-to-1, VI and VM.
PoS Induction test results
Results of my 2010 review of unsupervised PoS induction systems (paper).