sent2vec

TLDR: This library delivers numerical representations (features) for short texts or sentences, which can be used as input to any machine learning task later on. Think of it as an unsupervised version of FastText, and an extension of word2vec (CBOW) to sentences.

The method uses a simple but efficient unsupervised objective to train distributed representations of sentences. The algorithm outperforms the state-of-the-art unsupervised models on most benchmark tasks, and on many tasks even beats supervised models, highlighting the robustness of the produced sentence embeddings, see the paper for more details.

Setup & Requirements

Our code builds upon Facebook's FastText library, see also their nice documentation and python interfaces.

To compile the library, simply run a make command.

Generating Features from Pre-Trained Models

Given a pre-trained model model.bin (download links see below), here is how to generate the sentence features for an input text. To generate the features, use the print-sentence-vectors command and the input text file needs to be provided as one sentence per line:

./fasttext print-sentence-vectors model.bin < text.txt

This will output sentence vectors (the features for each input sentence) to the standard output, one vector per line. This can also be used with pipes:

cat text.txt | ./fasttext print-sentence-vectors model.bin

If you decide to download and use one of our models, it is also possible to use the python code provided in the get_sentence_embeddings_from_pre-trained_models notebook. It handles tokenization and can be given raw sentences.

Using Sentence level nearest neighbour search and analogies

Given a pre-trained model model.bin , here is how to use these features. For the nearest neighbouring sentence feature, you need the model as well as a corpora in which you can search for the nearest neighbouring sentence to your input sentence. We use cosine distance as our distance metric. To do so, we use the command nnSent and the input should be 1 sentence per line:

./fasttext nnSent model.bin corpora [k] 

k is optional and is the number of nearest sentences that you want to output.

For the analogiesSent, the user inputs 3 sentences A,B and C and finds a sentence from the corpora which is the closest to D in the A:B::C:D analogy pattern.

./fasttext analogiesSent model.bin corpora [k]

k is optional and is the number of nearest sentences that you want to output.

Downloading Pre-Trained Models

• sent2vec_wiki_unigrams 5GB (600dim, trained on english wikipedia)
• sent2vec_wiki_bigrams 16GB (700dim, trained on english wikipedia)
• sent2vec_twitter_unigrams 13GB (700dim, trained on english tweets)
• sent2vec_twitter_bigrams 23GB (700dim, trained on english tweets)
• sent2vec_toronto books_unigrams 2GB (700dim, trained on the BookCorpus dataset)
• sent2vec_toronto books_bigrams 7GB (700dim, trained on the BookCorpus dataset)

(as used in the arXiv paper)

Note: users who downloaded models prior to this release will encounter compatibility issues when trying to use the old models with the latest commit. Those users can still use the code in the release to keep using old models.

Tokenizing

Both feature generation as above and also training as below do require that the input texts (sentences) are already tokenized. To tokenize and preprocess text for the above models, you can use

python3 tweetTokenize.py <tweets_folder> <dest_folder> <num_process>

for tweets, or then the following for wikipedia:

python3 wikiTokenize.py corpora > destinationFile

Note: For wikiTokenize.py, set the SNLP_TAGGER_JAR parameter to be the path of stanford-postagger.jar which you can download here

Training New Models

To train a new sent2vec model, you first need some large training text file. This file should contain one sentence per line. The provided code does not perform tokenization and lowercasing, you have to preprocess your input data yourself, see above.

You can then train a new model. Here is one example of command:

./fasttext sent2vec -input wiki_sentences.txt -output my_model -minCount 8 -dim 700 -epoch 9 -lr 0.2 -wordNgrams 2 -loss ns -neg 10 -thread 20 -t 0.000005 -dropoutK 4 -minCountLabel 20 -bucket 4000000

Here is a description of all available arguments:

sent2vec -input train.txt -output model

The following arguments are mandatory:
  -input              training file path
  -output             output file path

The following arguments are optional:
  -lr                 learning rate [0.2]
  -lrUpdateRate       change the rate of updates for the learning rate [100]
  -dim                dimension of word and sentence vectors [100]
  -epoch              number of epochs [5]
  -minCount           minimal number of word occurences [5]
  -minCountLabel      minimal number of label occurences [0]
  -neg                number of negatives sampled [10]
  -wordNgrams         max length of word ngram [2]
  -loss               loss function {ns, hs, softmax} [ns]
  -bucket             number of hash buckets for vocabulary [2000000]
  -thread             number of threads [2]
  -t                  sampling threshold [0.0001]
  -dropoutK           number of ngrams dropped when training a sent2vec model [2]
  -verbose            verbosity level [2]

References

When using this code or some of our pre-trained models for your application, please cite the following paper:

Matteo Pagliardini, Prakhar Gupta, Martin Jaggi, Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features arXiv

@article{pgj2017unsup,
  title = {{Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features}},
  author = {Pagliardini, Matteo and Gupta, Prakhar and Jaggi, Martin},
  journal = {arXiv},
  eprint = {1703.02507},
  eprinttype = {arxiv},
  eprintclass = {cs.CL},
  year = {2017}
}