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 consume a sequence of graphemes then emit output a sequence of phonemes representing the pronunciation of that grapheme sequence in one of fifteen languages. Nine teams submitted a total of 23 systems, at best achieving an 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.
展开▼
