Download Latest Version Python 3.5 Support, Sampler Pipelining, Finer Control of Random State, New Corporate Sponsor source code.zip (861.1 kB)
Email in envelope

Get an email when there's a new version of PyTorch Natural Language Processing

Home / 0.3.0
Name Modified Size InfoDownloads / Week
Parent folder
0.3.0.tar.gz 2018-05-06 861.2 kB
0
0.3.0.zip 2018-05-06 926.8 kB
0
README.md 2018-05-06 1.4 kB
0
Totals: 3 Items   1.8 MB 0

Release 0.3.0

Major Features And Improvements

  • Upgraded to PyTorch 0.4.0
  • Added Byte-Pair Encoding (BPE) pre-trained subword embeddings in 275 languages
  • Refactored download scripts to torchnlp.downloads
  • Enable Spacy encoder to run in multiple languages.
  • Added a boolean aligned option to FastText supporting MUSE (Multilingual Unsupervised and Supervised Embeddings)

Bug Fixes and Other Changes

  • Create non-existent cache dirs for torchnlp.word_to_vector.
  • Add set operation to torchnlp.datasets.Dataset with support for slices, columns and rows
  • Updated biggest_batches_first in torchnlp.samplers to be more efficient at approximating memory then Pickle
  • Enabled torch.utils.pad_tensor and torch.utils. pad_batch to support N dimensional tensors
  • Updated to sacremoses to fix NLTK moses dependancy for torch.text_encoders

  • Added __getitem()__ for _PretrainedWordVectors. For example:

    from torchnlp.word_to_vector import FastText vectors = FastText() tokenized_sentence = ['this', 'is', 'a', 'sentence'] vectors[tokenized_sentence] - Added __contains__ for _PretrainedWordVectors. For example:

    from torchnlp.word_to_vector import FastText vectors = FastText()

    'the' in vectors True 'theqwe' in vectors False

Source: README.md, updated 2018-05-06