Daniele Bonadiman

Injecting Relational Structural Representation in Neural Networks for\n Question Similarity

2018 · arXiv (Cornell University)

Effectively using full syntactic parsing information in Neural Networks (NNs)\nto solve relational tasks, e.g., question similarity, is still an open problem.\nIn this paper, we propose to inject structural representations in NNs by (i)\nlearning an SVM …