epsilon-compositionality

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

commit 89ecbc82e8676173046e20dfce6653e7c92c3b06
parent cbf9c61e2d82a75dd4e851d3ca40f420488245a3
Author: Γ‰tienne Simon <esimon@esimon.eu>
Date:   Tue,  7 Oct 2025 10:30:14 +0200

Fix title/improve README

Diffstat:
MREADME.md | 7+++----
1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md @@ -1,13 +1,12 @@ -# Evaluating Idiomaticity in Sentence Embeddings with πœ€-compositionality +# Measuring Idiomaticity in Text Embedding Models with πœ€-compositionality -To reproduce everything: +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: ```sh git clone --recurse-submodules THIS_REPOSITORY python -m epsilon_compositionality ``` -The data is included as a git submodule, from there the python module `epsilon_compositionality` run all the necessary code and output a `results` directory containing the LaTeX code we included in the article. -This is equivalent to: +For a more decomposed (pun intended) approach, this is equivalent to: ```sh python -m epsilon_compositionality.build_dataset python -m epsilon_compositionality.extract_similarities