Low-Resource G2P and P2G Conversion with Synthetic Training Data

Low-Resource G2P and P2G Conversion with Synthetic Training Data Bradley Hauer author Amir Ahmad Habibi author Yixing Luan author Arnob Mallik author Grzegorz Kondrak author 2020-jul text Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology Association for Computational Linguistics Online conference publication This paper presents the University of Alberta systems and results in the SIGMORPHON 2020 Task 1: Multilingual Grapheme-to-Phoneme Conversion. Following previous SIGMORPHON shared tasks, we define a low-resource setting with 100 training instances. We experiment with three transduction approaches in both standard and low-resource settings, as well as on the related task of phoneme-to-grapheme conversion. We propose a method for synthesizing training data using a combination of diverse models. hauer-etal-2020-low https://www.aclweb.org/anthology/2020.sigmorphon-1.12 2020-jul 117 122