Project roadmapΒΆ

Vecto is work in progress. Everything that works at the moment is described in the present tutorial; feel free to get in touch if anything is not clear. Also, new functionality is coming in the nearest months, so check back for more features!

DONE IN PROGRESS
   
General:
  • Loading various vsm formats: plain text, npy, binary, h5p
  • Metadata generation
  • Basic vector operations, efficient similarity search
  • VSM visualization
  • Pretty data downloader for benchmarks
   
VSM generation:
  • word2vec
    • Character-level VSM
  • GloVe
  • SVD
   
VSM evaluation:
  • 6 methods of solving word analogies
  • similarity and relatedness tests
  • text classification
  • sequence labeling (POS-tagging, chunking, NER)
  • natural language inference
  • language modeling
  • neural machine translation
  • subjectivity classification
  • and more!