Fig. 2
From: C-Norm: a neural approach to few-shot entity normalization

Architecture of the Single Layer Feedforward Neural Network. The input is the matrix of word embeddings of the non-stopword tokens of the mentions
From: C-Norm: a neural approach to few-shot entity normalization
Architecture of the Single Layer Feedforward Neural Network. The input is the matrix of word embeddings of the non-stopword tokens of the mentions