Abstract
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.
Cite
CITATION STYLE
Zhou, C., & Neubig, G. (2017). Morphological Inflection Generation with Multi-space Variational Encoder-Decoders. In CoNLL 2017 - Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection (pp. 58–65). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/k17-2005
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
