Skip to content
Pre-release

@giacbrd giacbrd released this Dec 30, 2016 · 15 commits to master since this release

  • Online learning and better pre-training in GensimFastTex:
    • Hashing trick for building the vocabulary, similar to the original fastText approach
    • It is possible to pre-fit word embeddings from a dataset with word2vec
    • True online earning with partial_fit, the vocabulary is incrementally updated
  • New version of fastText.py: 0.8.2
  • New version of Gensim: 0.13.4
  • Fixed predict_proba output format
Assets 2
Pre-release

@giacbrd giacbrd released this Nov 6, 2016 · 75 commits to master since this release

  • Faster prediction for multiple labels with one predict call
  • Better persistence with save and load methods
  • Fixed parameter names convention
Assets 2
Pre-release
Pre-release

@giacbrd giacbrd released this Oct 27, 2016 · 102 commits to master since this release

  • FastText classifier based on version 0.8.0 of https://github.com/salestock/fastText.py
  • GensimFastText has now:
    • negative sampling
    • softmax as alternative output function
    • almost complete LabeledWord2Vec as subclass of Gensim's Word2Vec
  • More tests
Assets 2
Pre-release
Pre-release

@giacbrd giacbrd released this Oct 13, 2016 · 159 commits to master since this release

this is broken, valid commit for this release is 263bfb1

  • Cython code for fastText in Gensim
  • Script for benchmarks
Assets 2
Pre-release
Pre-release

@giacbrd giacbrd released this Oct 11, 2016 · 197 commits to master since this release

  • GensimFTClassifier can train and predict
Assets 2
You can’t perform that action at this time.