Audience-Centric Natural Language Generation via Style Infusion

by   Samraj Moorjani, et al.

Adopting contextually appropriate, audience-tailored linguistic styles is critical to the success of user-centric language generation systems (e.g., chatbots, computer-aided writing, dialog systems). While existing approaches demonstrate textual style transfer with large volumes of parallel or non-parallel data, we argue that grounding style on audience-independent external factors is innately limiting for two reasons. First, it is difficult to collect large volumes of audience-specific stylistic data. Second, some stylistic objectives (e.g., persuasiveness, memorability, empathy) are hard to define without audience feedback. In this paper, we propose the novel task of style infusion - infusing the stylistic preferences of audiences in pretrained language generation models. Since humans are better at pairwise comparisons than direct scoring - i.e., is Sample-A more persuasive/polite/empathic than Sample-B - we leverage limited pairwise human judgments to bootstrap a style analysis model and augment our seed set of judgments. We then infuse the learned textual style in a GPT-2 based text generator while balancing fluency and style adoption. With quantitative and qualitative assessments, we show that our infusion approach can generate compelling stylized examples with generic text prompts. The code and data are accessible at


page 1

page 2

page 3

page 4


Multi-dimensional Style Transfer for Partially Annotated Data using Language Models as Discriminators

Style transfer has been widely explored in natural language generation w...

Prompt-Based Editing for Text Style Transfer

Prompting approaches have been recently explored in text style transfer,...

StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model

Despite the progress made in the style transfer task, most previous work...

SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation

Supervised training of abstractive language generation models results in...

A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

Unsupervised text style transfer aims to transfer the underlying style o...

Stylistic Retrieval-based Dialogue System with Unparallel Training Data

The ability of a dialog system to express consistent language style duri...

(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas

Stylistic variation in text needs to be studied with different aspects i...

Please sign up or login with your details

Forgot password? Click here to reset