Explaining Neural Language Models from Internal Representations to Model Predictions | Gabriele Sarti

Explaining Neural Language Models from Internal Representations to Model Predictions

Gabriele Sarti, Alessio Miaschi
Natural Language Processing, Academic
Project Lab Materials

Date
May 31, 2023
Event
Lab at AILC Lectures on Computational Linguistics 2023
Location
University of Pisa, Italy
Natural Language Processing Interpretability Sequence-to-sequence Language Modeling Feature Attribution Probing Classifiers

Related