Long short-term memory networks (LSTM) achieve great success in temporal dependency modeling for chain-structured data, such as texts and speeches. An extension toward more complex data structures as encountered in 2D graphic languages is proposed in this work. Specifically, we address the problem of handwritten mathematical expression recognition, using a tree-based BLSTM architecture allowing the direct labeling of nodes (symbol) and edges (relationship) from a graph modeling the input strokes. One major difference with the traditional approaches is that there is no explicit segmentation, re...
