Facilitating the Communication of Politeness through Fine-Grained Paraphrasing

Abstract

Aided by technology, people are increasingly able to communicate across geographical, cultural, and language barriers. This ability also results in new challenges, as interlocutors need to adapt their communication approaches to increasingly diverse circumstances. In this work, we take the first steps towards automatically assisting people in adjusting their language to a specific communication circumstance. As a case study, we focus on facilitating the accurate transmission of pragmatic intentions and introduce a methodology for suggesting paraphrases that achieve the intended level of politeness under a given communication circumstance. We demonstrate the feasibility of this approach by evaluating our method in two realistic communication scenarios and show that it can reduce the potential for misalignment between the speaker's intentions and the listener's perceptions in both cases.

Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark

“…NLP Studies on Social Information Numerous studies have contributed to the development of datasets and models aimed toward identifying nuanced social information in language across diverse contexts. Computational linguists have modeled multiple forms of social information in language like sentiment , politeness (Fu et al, 2020), humor (Meaney et al, 2021), offensiveness (ElSherief et al, 2021), and intimacy (Pei and Jurgens, 2020), often achieving state-of-the-art results close to human performance in their respective settings. Studies such as Park et al (2021) have also leveraged explicitly-given norms to train models to be more accurate in contextspecific situations.…”

“…Other Social Factors Finally, we include tasks of a more discursive and rhetorical type, that are understood to be more reliant on the contextual elements of social distance, power, and solidarity. In SOCKET, the tasks included are empathy (Buechel et al, 2018), politeness (Hayati et al, 2021Fu et al, 2020), intimacy (Pei and Jurgens, 2020) and complaints (Preoţiuc-Pietro et al, 2019). Politeness, like humor, is understood to be a noncooperative prosocial behavior but unlike humor, is concerned with the act of "saving face" .…”

Comparing Styles across Languages

“…Danescu-Niculescu-Mizil et al ( 2013) presents one of the earliest quantitative analyses of linguistic politeness, with Srinivasan and Choi (2022) following in a multilingual setting. Other computational work focusing on politeness uses LMs to generate or modify text with a specified politeness level (Niu and Bansal, 2018;Fu et al, 2020;Mishra et al, 2022;Silva et al, 2022).…”

Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach

“…Computational methods that can perform empathic rewriting can be used for suggesting ways to make conversations more empathic in similar feedback and training systems for mental health support and counseling. In a related context, researchers have built AI tools for writing assistance in negotiations [68], composing emails [8], language translation [50], creative writing [9], and communication of politeness [18].…”