fowler.corpora
is software to create vector space models for distributional semantics.
It is possible to instantiate a vector space from
- Brown corpus
- British National Corpus
- ukWac and WaCkypedi
The weighting schemes include:
- TF-IDF
- NMF
- PMI
- PPMI
- nIITF
The implemented experiments are:
- Word similarity
- SimLex-999
- Men
- Sentence similarity