generalised-brown: Source code for AAAI 2016 paper
Sean Chester, Leon Derczynski · Zenodo (CERN European Organization for Nuclear Research) · 2015
This is the first release of the generalised-brown software. It consists of two modules for constructing clusters of word types: The merge_generator module is an extension of Brown clustering (based on the C++11 implementation of wcluster) that tracks state in the form of a merge log The cluster_generator is a python script that reconstructs the state of the Brown clustering algorithm from the merge log in order to vary the granularity of the output clusters.