1 code implementation • 31 Dec 2021 • Sílvia Casacuberta, Esra Suel, Seth Flaxman
In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs).
1 code implementation • Findings (ACL) 2021 • Sílvia Casacuberta, Karina Halevy, Damián E. Blasi
We find moderate to strong positive correlations between categorical modularity and performance on the monolingual tasks of sentiment analysis and word similarity calculation and on the cross-lingual task of bilingual lexicon induction both to and from English.