The SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion
By Kyle Gorman, Lucas F. E. Ashby, Aaron Goyzueta, Arya D. McCarthy, Shijie Wu, Daniel You. 2020
56 citations recorded by the source corpus.
We describe the design and findings of the SIGMORPHON 2020 shared task on multilingual grapheme-to-phoneme conversion. Participants were asked to submit systems which take in a sequence of graphemes in a given language as input, then output a sequence of phonemes representing the pronunciation of that grapheme sequence. Nine teams submitted a total of 23 systems, at best achieving a 18% relative reduction in word error rate (macro-averaged over languages), versus strong neural sequence-to-sequence baselines. To facilitate error analysis, we publicly release the complete outputs for all systems—a first for the SIGMORPHON workshop.
Subfields: Artificial Intelligence, Natural Language Processing, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Colin Raffel
- Mohit Bansal
- Luke S. Zettlemoyer
- Yejin Choi
- Percy Liang
- Adam Roberts
- Noah Constant
- Hannaneh Hajishirzi
In Natural Language Processing
- Colin Raffel
- Mihir Kale
- Noah Constant
- Rami Al-Rfou
- André F. T. Martins
- Adam Roberts
- Sharan Narang
- Linting Xue
In Evaluation & Benchmarks
- Rami Al-Rfou
- Adam Roberts
- André F. T. Martins
- Jonas Kuhn
- Aditya Barua
- Colin Raffel
- Mihir Kale
- Linting Xue
Citations in the corpus
- ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models (2021, background): “Multilingual grapheme-to-phoneme conversion (Gorman et al., 2020) covers 15 languages and requires mapping a word to its pronunciation as phonemes (e.g. cat→ /kæt/).”
- Ensemble Self-Training for Low-Resource Languages: Grapheme-to-Phoneme Conversion and Morphological Inflection (2020, methodology): “We apply the framework on two of the SIGMOR-PHON 2020 Shared Tasks: grapheme-to-phoneme conversion (Gorman et al., 2020) and morphological inflection (Vylomova et al., 2020).”
- One-Size-Fits-All Multilingual Models (2020, background): “We make four submissions to Task 1 (Gorman et al., 2020), which differ based on their choice of softmax replacement ( 1 .”