UNAM at SemEval-2018 Task 10: Unsupervised Semantic Discriminative Attribute Identification in Neural Word Embedding Cones

no code implementations • SEMEVAL 2018 • Ignacio Arroyo-Fern{\'a}ndez, Ivan Meza, Carlos-Francisco M{\'e}ndez-Cruz

As $a, b, q$ are represented with neural word embeddings, we tested vector operations allowing us to measure membership, i. e. fuzzy set operations (t-norm, for fuzzy intersection, and t-conorm, for fuzzy union) and the similarity between $q$ and the convex cone described by $a$ and $b$.

Attribute Word Embeddings