epsilon-compositionality

Code for our paper Measuring Idiomaticity in Text Embedding Models with 𝜀-compositionality
git clone https://esimon.eu/repos/epsilon-compositionality.git
Log | Files | Refs | Submodules | README

README.md (667B)

      1 # Measuring Idiomaticity in Text Embedding Models with 𝜀-compositionality
      2 
      3 The data is included as a git submodule, from there the python module `epsilon_compositionality` runs all the necessary code and outputs a `results` directory containing the LaTeX code we included in the article. To reproduce everything, run the following:
      4 ```sh
      5 git clone --recurse-submodules THIS_REPOSITORY
      6 python -m epsilon_compositionality
      7 ```
      8 
      9 For a more decomposed (pun intended) approach, this is equivalent to:
     10 ```sh
     11 python -m epsilon_compositionality.build_dataset
     12 python -m epsilon_compositionality.extract_similarities
     13 python -m epsilon_compositionality.compute_statistics
     14 ```