Morphological Inflection Generation with Multi-space Variational Encoder-Decoders
Chunting Zhou, Graham Neubig · 2017
This paper describes the CMU submission to shared task 1 of SIGMORPHON 2017.The system is based on the multi-space variational encoder-decoder (MSVED) method of Zhou and Neubig (2017), which employs both continuous and discrete latent variables for the variational encoder-decoder and is trained in a semi-supervised fashion.We discuss some language-specific errors and present result analysis.