Politeness Transfer: A Tag and Generate Approach

By Aman Madaan, Amrith Rajagopal Setlur, Tanmay Parekh, Barnab'as P'oczos, Graham Neubig, Yiming Yang, Ruslan Salakhutdinov, Alan W. Black, Shrimai Prabhumoye. 2020

174 citations recorded by the source corpus.

This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning. We also provide a dataset of more than 1.39 instances automatically labeled for politeness to encourage benchmark evaluations on this new task. We design a tag and generate pipeline that identifies stylistic attributes and subsequently generates a sentence in the target style while preserving most of the source content. For politeness as well as five other transfer tasks, our model outperforms the state-of-the-art methods on automatic metrics for content preservation, with a comparable or better performance on style transfer accuracy. Additionally, our model surpasses existing methods on human evaluations for grammaticality, meaning preservation and transfer accuracy across all the six style transfer tasks. The data and code is located at https://github.com/tag-and-generate.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “Arabic-speaking cultures, on the other hand, might ﬁnd this use awkward, if not rude, in conversations among close friends (K ´ ad ´ ar & Mills, 2011; Madaan et al., 2020).”
Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design (2022, background): “Arabic-speaking cultures, on the other hand, might find this use awkward, if not rude, in conversations among close friends (Kádár and Mills, 2011; Madaan et al., 2020).”
A Recipe for Arbitrary Text Style Transfer with Large Language Models (2021, background): “She wanted her poem to be cheerful like it used to be, but couldn’t ﬁnd the right words. cal slant (Prabhumoye et al., 2018; Madaan et al., 2020; Liu et al., 2021b).”
Tailor: Generating and Perturbing Text with Semantic Controls (2021, methodology): “Given these perturbed control codes in the input (C), T ailor generates a new sentence (D) that reﬂects the desired perturbations. a sentiment style transferer requires instances annotated with positive and negative labels (Madaan et al., 2020b).”
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models (2021, background): “control through predefined style attributes or labels (Madaan et al., 2020; Malmi et al., 2020).”
Text Detoxification using Large Pre-trained Neural Models (2021, background): “The style transfer task is generally understood as rewriting of text with the same content and with altering of one or several attributes which constitute the “style”, such as authorship (Voigt et al., 2018), sentiment (Shen et al., 2017), or degree of politeness (Madaan et al., 2020).”
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer (2021, methodology): “…et al. (2017); John et al. (2019) or (2) using unsupervised generative approaches from retrieval (Li et al., 2018), tagging using style phrases (Madaan et al., 2020), to back-translation and unsupervised machine translation techniques (Prabhumoye et al., 2018; Lample et al., 2019; He et al.,…”
Explaining The Efficacy of Counterfactually-Augmented Data (2020, methodology): “…set of experiments, we rely on four state of the art style transfer models representative of diﬀerent methodologies, each representative of a diﬀerent approach to automatically generate new examples with ﬂipped labels (Hu et al., 2017; Li et al., 2018; Sudhakar et al., 2019; Madaan et al., 2020).”
Deep Learning for Text Style Transfer: A Survey (2020, methodology): “Because these generation practices are complicated, Madaan et al. (2020) propose a simpler way.”
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer (2021, methodology): “, 2020), and Retrieve-and-Edit approaches (Li et al., 2018; Hashimoto et al., 2018; Guu et al., 2018; Sudhakar et al., 2019; Madaan et al., 2020).”
Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework (2021, unknown): “In NLP, previously analyzed style dimensions include formal/informal, simple/complex, abstract/concrete and polite/impolite (Pavlick and Nenkova, 2015; Pavlick and Tetreault, 2016; Paetzold and Specia, 2016; Brooke and Hirst, 2013; Madaan et al., 2020).”
Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models (2022, methodology): “The first family of approaches involves identifying and replacing distinctive style-related phrases (Li et al. (2018); Sudhakar et al. (2019); Wu et al. (2019); Madaan et al. (2020); Malmi et al. (2020); Reid and Zhong (2021), inter alia).”
The Importance of Modeling Social Factors of Language: Theory and Practice (2021, background): “While it is common amongst native speakers of North American English to use “ please ” in requests even to close friends, such an act would be considered awkward, if not rude, in Arabic-speaking cultures (Kádár and Mills, 2011; Madaan et al., 2020).”
PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits (2023, background): “…et al., 2016; Tadesse et al., 2018), and personalized dialogue generation (Mairesse and Walker, 2007, 2011; Zhang et al., 2018; Qian et al., 2018) including stylistic transfer of personality traits such as formality and polite-ness (Kabbara and Cheung, 2016; Jin et al., 2019; Madaan et al., 2020).”