Guess who? Multilingual approach for the automated generation of author-stylized poetry
This addresses the problem of automated creative text generation for multilingual applications, but it is incremental as it builds on existing LSTM methods with enhancements.
The paper tackled multilingual stylized poetry generation by using an LSTM model with extended phonetic and semantic embeddings, showing it outperformed baselines in BLEU scores and human evaluations associating generated texts with target authors.
This paper addresses the problem of stylized text generation in a multilingual setup. A version of a language model based on a long short-term memory (LSTM) artificial neural network with extended phonetic and semantic embeddings is used for stylized poetry generation. The quality of the resulting poems generated by the network is estimated through bilingual evaluation understudy (BLEU), a survey and a new cross-entropy based metric that is suggested for the problems of such type. The experiments show that the proposed model consistently outperforms random sample and vanilla-LSTM baselines, humans also tend to associate machine generated texts with the target author.