Improving sequence to sequence learning for morphological inflection generation: The biu-mit systems for the SIGMORPHON 2016 shared task for morphological reinflection

Abstract

Morphological reinflection is the task of generating a target form given a source form and the morpho-syntactic attributes of the target (and, optionally, of the source). This work presents the submission of Bar Ilan University and the Massachusetts Institute of Technology for the morphological reinflection shared task held at SIGMORPHON 2016. The submission includes two recurrent neural network architectures for learning morphological reinflection from incomplete inflection tables while using several novel ideas for this task: morpho-syntactic attribute embeddings, modeling the concept of templatic morphology, bidirectional input character representations and neural discriminative string transduction. The reported results for the proposed models over the ten languages in the shared task bring this submission to the second/third place (depending on the language) on all three sub-tasks out of eight participating teams, while training only on the Restricted category data.