Header

UZH-Logo

Maintenance Infos

CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion


Makarov, Peter; Clematide, Simon (2020). CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion. In: Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, Online, 1 July 2020 - 1 July 2020.

Abstract

This paper describes the submission by the team from the Institute of Computational Linguistics, Zurich University, to the Multilingual Grapheme-to-Phoneme Conversion (G2P) Task of the SIGMORPHON 2020 challenge. The submission adapts our system from the 2018 edition of the SIGMORPHON shared task. Our system is a neural transducer that operates over explicit edit actions and is trained with imitation learning. It is well-suited for morphological string transduction partly because it exploits the fact that the input and output character alphabets overlap. The challenge posed by G2P has been to adapt the model and the training procedure to work with disjoint alphabets. We adapt the model to use substitution edits and train it with a weighted finite-state transducer acting as the expert policy. An ensemble of such models produces competitive results on G2P. Our submission ranks second out of 23 submissions by a total of nine teams.

Abstract

This paper describes the submission by the team from the Institute of Computational Linguistics, Zurich University, to the Multilingual Grapheme-to-Phoneme Conversion (G2P) Task of the SIGMORPHON 2020 challenge. The submission adapts our system from the 2018 edition of the SIGMORPHON shared task. Our system is a neural transducer that operates over explicit edit actions and is trained with imitation learning. It is well-suited for morphological string transduction partly because it exploits the fact that the input and output character alphabets overlap. The challenge posed by G2P has been to adapt the model and the training procedure to work with disjoint alphabets. We adapt the model to use substitution edits and train it with a weighted finite-state transducer acting as the expert policy. An ensemble of such models produces competitive results on G2P. Our submission ranks second out of 23 submissions by a total of nine teams.

Statistics

Citations

Altmetrics

Downloads

3 downloads since deposited on 03 Feb 2021
3 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Lecture), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:1 July 2020
Deposited On:03 Feb 2021 07:02
Last Modified:07 Feb 2021 08:53
Publisher:Association for Computational Linguistics
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.18653/v1/2020.sigmorphon-1.19

Download

Hybrid Open Access

Download PDF  'CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion'.
Preview
Content: Published Version
Filetype: PDF
Size: 481kB
View at publisher
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)