CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion
| Autor: | Simon Clematide, Peter Makarov |
|---|---|
| Přispěvatelé: | University of Zurich |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Character (computing) String (computer science) Substitution (logic) Grapheme 410 Linguistics Disjoint sets Transduction (psychology) 000 Computer science knowledge & systems computer.software_genre Task (project management) 10105 Institute of Computational Linguistics Artificial intelligence Computational linguistics business computer Natural language processing |
| Zdroj: | SIGMORPHON |
| DOI: | 10.5167/uzh-198771 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|