Skip to content

Neural ParsCit v1.0.3 (Optimisation)
Compare
Choose a tag to compare
@kylase kylase released this 20 Aug 12:57
· 18 commits to master since this release
v1.0.3
f4ad0ba
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

Release Notes

  • freq is not longer required as the entire word vectors provided by WING can be loaded with lower peak memory usage than the v1.0.2
  • Added environment variable ENVIRONMENT to the Docker container. You may want to rebuild your image.
  • If the <UNK> is not provided in the word embeddings, the embedding layer will issue a warning about higher memory consumption as it will add it into the word embeddings in memory (< 7.5 GB)
  • Otherwise, if <UNK> exists in the word embeddings, it will be more memory efficient (< 4.5 GB). You will need to get the word embeddings with <UNK> from README
  • Introduced model evaluation (skipped in CI due to insufficient memory)
    • v1.0.2 (macro f1: 0.984859387481312, micro f1: 0.9935205183585313)
    • v1.0.3 (macro f1: 0.9843960859239398, micro f1: 0.9933405327573794)

Important Notes

  • This version is the last supported version for Theano-based Neural ParsCit unless major issues are discovered
  • The model will be ported to PyTorch in v1.1 and will support Python 3.5+ only
  • The word embeddings without <UNK> and freq files will not be downloadable in v1.0.4
  • The existing files: word vectors (vectors.tar.gz and freq) will be removed from WING website in v1.0.4
Assets 2
Loading