Search Results for author: Francesco Ackermann

Found 1 papers, 0 papers with code

Vectorial Semantic Spaces Do Not Encode Human Judgments of Intervention Similarity

no code implementations CONLL 2018 Paola Merlo, Francesco Ackermann

We present results that show, under exhaustive and precise conditions, that one kind of word embeddings and the similarity spaces they define do not encode the properties of intervention similarity in long-distance dependencies, and that therefore they fail to represent this core linguistic notion.

Word Embeddings

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