Search Results for author: Mario Mezzanzanica

Found 3 papers, 2 papers with code

Contrastive Explanations of Text Classifiers as a Service

no code implementations NAACL (ACL) 2022 Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani, Andrea Seveso

The recent growth of black-box machine-learning methods in data analysis has increased the demand for explanation methods and tools to understand their behaviour and assist human-ML model cooperation.

Embeddings Evaluation Using a Novel Measure of Semantic Similarity

1 code implementation Cognitive Computation 2022 Anna Giabelli, Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani

Then, we train several embedding models on a text corpus and select the best model, that is, the model that maximizes the correlation between the HSS and the cosine similarity of the pair of words that are in both the taxonomy and the corpus.

Embeddings Evaluation Semantic Similarity +1

ContrXT: Generating Contrastive Explanations from any Text Classifier

1 code implementation Information Fusion 2021 Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Andrea Seveso, Navid Nobani

The need for explanations of ML systems is growing as new models outperform their predecessors while becoming more complex and less comprehensible for their end-users.

Decision Making Explainable artificial intelligence +2

Cannot find the paper you are looking for? You can Submit a new open access paper.