TST has many immediate applications. 

(1) Intelligent bots, for which users prefer distinct and consistent persona (e.g., empathetic) instead of emotionless or inconsistent persona.

(2) Intelligent writing assistants; for example, non-expert writers often need to polish their writing to better fit their purpose, for example, more professional, polite, objective, humorous, or other advanced writing requirements, which may take years of experience to master. 

(3) Automatic text simplification (where the target style is “simple”), debiasing online text (where the target style is “objective”), fighting against offensive language (where the target style is “non-offensive”), and so on.

Hamilton College

To formally define TST, let us denote the target utterance as x' and the target discourse style attribute as a'. TST aims to model p(x'|a, x), where x is a given text carrying a source attribute value a. 

Text Style Transfer (TST)

Jin, Di, et al. “Deep Learning for Text Style Transfer: A Survey.” ACL Anthology, https://aclanthology.org/2022.cl-1.6/. 

Deep Learning for Text Style Transfer: A Survey

The goal of TST is to automatically control the style attributes of text while preserving the content. The style of language is crucial because it makes
natural language processing more user-centered.

The Goal of TST

The Applications of TST

Crucial to the definition of style transfer is the distinction of “style” and “content,” for which there are two common practices. The first one is by linguistic definition, where non-functional linguistic features are classified into the style (e.g., formality), and the semantics are classified into the content. In contrast, the second practice is data-driven given two corpora (e.g., a positive review set and a negative review set), the invariance between the two corpora is the content, whereas the variance is the style (e.g., sentiment, topic).

Difference between Style and Content

With the success of deep learning in the last decade, a variety of neural methods have been recently proposed for TST. If parallel data are provided, standard sequence-to-sequence models are often directly applied. However, most use cases do not have parallel data, so TST on non-parallel corpora has
become a prolific research area

Approaches of TST

The existing literature of TST shows a large diversity in the selection of benchmark datasets, methodological frameworks, and evaluation metrics.

Aspects of TST

The style transfer tasks mainly discuss task formulation and introducing the notations that will be used. It also lists all the common subtasks for neural TST which can save the literature review efforts for future researchers.

Learn Before

Related