Using BLSTM for Interpretation of 2D Languages - Case of Handwritten Mathematical Expressions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Using BLSTM for Interpretation of 2D Languages - Case of Handwritten Mathematical Expressions

Résumé

In this work, we study how to extend the capability of BLSTM networks to process data which are not only text strings but graphical two-dimensional languages such as handwrit- ten mathematical expressions. The proposed solution aims at transforming the mathematical expression description into a sequence including at the same time symbol labels and relation- ship labels, so that classical supervised sequence labeling with recurrent neural networks can be applied. For simple one-dimensional (1-D) expression, we use the Right label to segment one symbol from the next one, as with the standard blank label for regular text. For genuine two- dimensional (2-D) expressions, we introduce additional specific labels assigned to each of the different possible spatial relationships that exist between sub-expressions. As a result, BLSTM network is able to perform at the same time the symbol recognition task and the segmentation task, which is a new perspective for the mathematical expression domain.
Fichier non déposé

Dates et versions

hal-01576308 , version 1 (22-08-2017)

Identifiants

  • HAL Id : hal-01576308 , version 1

Citer

Ting Zhang, Harold Mouchère, Christian Viard-Gaudin. Using BLSTM for Interpretation of 2D Languages - Case of Handwritten Mathematical Expressions. Colloque International Francophone sur l’Écrit et le Document 2016 (CIFED), Mar 2016, Toulouse, France. ⟨hal-01576308⟩
506 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More