Marvin is an AI powered tool for stylistic language editing. It leverages a combination of recent Natural Language Processing (NLP) and deep learning innovations in text classification and generation as well as visualization and interpretation techniques. Marvin provides the ability to classify the style of texts, transfer to other styles as well as understand how certain features contribute to style. It strives to adhere to a machine-in-the-loop framework, where writing is performed normally by human users, but is aided by algorithmic suggestions.
We evaluated the machine learning models that comprise Marvin on several benchmark metrics and determined that these models are able to perform well on linguistic style tasks. One of Marvin’s primary novel contributions is the ability to transfer to different specific levels of a particular style. It also can perform joint style analysis and transfer for several dimensions of style simultaneously.