8a0e1141fd37fa5b98d5bb769ba1a7cc-Reviews.html

This paper aims at measuring the similarity between pairs of short texts using a neural network. Each input unit is associated with a set of words from each text. Each input unit first computes a bilinear match score from its pair of word sets. Then the rest of the network is more classical. The connectivity patterns between the network units, i.e. association of terms to input units and connection between layers comes from a multi-resolution topic model.