A syllable-level LSTM language model with multi-stage transfer learning generates Italian tercets that non-expert judges attribute to Dante about 28% of the time versus 64% for real Dante, with a relative difference of 56.25%.
In: Proceedings of the 27th International Conference on Computational Linguistics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural Poetry: Learning to Generate Poems using Syllables
A syllable-level LSTM language model with multi-stage transfer learning generates Italian tercets that non-expert judges attribute to Dante about 28% of the time versus 64% for real Dante, with a relative difference of 56.25%.