Learning Literary Style End-to-end with Artificial Neural Networks
Ivan P. Yamshchikov, Alexey Tikhonov · Advances in Science Technology and Engineering Systems Journal · 2019
This paper addresses the generation of stylized texts in a multilingual setup.A long short-term memory (LSTM) language model with extended phonetic and semantic embeddings is shown to capture poetic style when trained end-to-end without any expert knowledge.Phonetics seems to have a comparable contribution to the overall model performance as the information on the target author.The quality of the generated texts is estimated through bilingual evaluation understudy (BLEU), a new cross-entropy based metric, and a survey of human peers.When a style of target author is recognized by the humans, they do not seem to distinguish generated texts and originals.