# Lacking the embedding of a word? Look it up into a traditional dictionary
This folder contains all the code running experiments in the paper ``Lacking the embedding of a word? Look it up into a traditional dictionary''.
Tests presented in section 4 are runnable launching "all_tests" and "all_tests_bert".
Please note that pretrained embeddings are needed in directory "data/pretrained":
  - w2v (https://drive.google.com/file/d/0B7XkCwpI5KDYNlNUTTlSS21pQmM/edit?usp=sharing)
  - and fasttext (https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.en.300.bin.gz) are used.
Installation of the Core NLP server is needed too (https://stanfordnlp.github.io/CoreNLP/corenlp-server.html#getting-started)
Other dependencies are listed in requirements.txt.