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
commit d8dd3ff0325320ab64d2b33100334b3fec790bc4
parent 670984d25213a03afccea8bee91896f989485c85
Author: Sondre Wold <sondrewold1@gmail.com>
Date:   Mon, 18 Aug 2025 13:04:09 +0200

update run file

Diffstat:

Arun_experiments.sh | 5+++++


1 file changed, 5 insertions(+), 0 deletions(-)

diff --git a/run_experiments.sh b/run_experiments.sh
@@ -0,0 +1,5 @@
+for model in "BERT_cls" "BERT_mean" "S_BERT" "S_GPT" "E5" "QWEN"
+do
+		python experiment.py -data_path ncimp/ncip_context.csv -experiment_type ncip -normalization_value 0.0 -result_path ./results_cls -model $model
+		python experiment.py -data_path ncimp/ncip_context.csv -experiment_type ncip-non -normalization_value 0.0 -result_path ./results_cls -model $model
+done