Pinned Loading

1. i-machine-think/compositionality_paradox_mt i-machine-think/compositionality_paradox_mt Public

   Codebase for analysing compositional generalisation in NMT models, which allows you to run systematicity, productivity, substitutivity and idiom processing analyses.

   NewLisp 8 1

2. i-machine-think/morphology_and_generalisation i-machine-think/morphology_and_generalisation Public

   Repository with code for interpretability analyses of a recurrent neural network predicting German plural nouns.

   Python 3 1

3. mt_idioms mt_idioms Public

   Repository for the analysis of idiom processing in MarianMT Transformer, for models translating English into 1 of 7 European target languages.

   NewLisp 5 2

4. bottleneck_compositionality_metric bottleneck_compositionality_metric Public

   Compare Tree-LSTMs with and without a bottleneck to obtain a scalable compositionality metric (BCM).

   Jupyter Notebook 2

5. i-machine-think/am-i-compositional i-machine-think/am-i-compositional Public

   Python 62 8

6. memorisation_localisation memorisation_localisation Public

   Implementation for the ACL-Findings 2024 paper on memorisation localisation for NLP classification tasks.

   Jupyter Notebook 2