Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models
This addresses the challenge of automating stylistic text adaptation, which is currently manual, for applications in creative writing or education, though it is incremental as it builds on existing neural methods.
The paper tackled the problem of automatically transforming modern English text to Shakespearean English by developing a copy-enriched sequence-to-sequence neural model, achieving a BLEU score of 31+ which is about 6 points higher than the strongest baseline.
Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose. However, applying stylistic variations is still by and large a manual process, and there have been little efforts towards automating it. In this paper we explore automated methods to transform text from modern English to Shakespearean English using an end to end trainable neural model with pointers to enable copy action. To tackle limited amount of parallel data, we pre-train embeddings of words by leveraging external dictionaries mapping Shakespearean words to modern English words as well as additional text. Our methods are able to get a BLEU score of 31+, an improvement of ~6 points above the strongest baseline. We publicly release our code to foster further research in this area.