A two-step attention decoder, stem-based data hallucination, and multi-language transfer improve low-resource morphological inflection accuracy to 63.8% macro-averaged on the SIGMORPHON 2019 benchmark, 15 points over the prior state of the art.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Pushing the Limits of Low-Resource Morphological Inflection
A two-step attention decoder, stem-based data hallucination, and multi-language transfer improve low-resource morphological inflection accuracy to 63.8% macro-averaged on the SIGMORPHON 2019 benchmark, 15 points over the prior state of the art.