Politeness Transfer: A Tag and Generate Approach

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1869–1881 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 1869 Politeness Transfer: A Tag and Generate Approach Aman Madaan ∗, Amrith Setlur ∗, Tanmay Parekh ∗, Barnabas Poczos, Graham Neubig, Yiming Yang, Ruslan Salakhutdinov, Alan W Black, Shrimai Prabhumoye School of Computer Science Carnegie Mellon University Pittsburgh, PA, USA {amadaan, asetlur, tparekh}@cs.cmu.edu Abstract 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 million instances automatically labeled for politeness to encourage benchmark evaluations on this new task. We design a tag and generate pipeline that identifies stylistic at- tributes 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 accu- racy. Additionally, our model surpasses exist- ing methods on human evaluations for gram- maticality, 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/ 1 Introduction Politeness plays a crucial role in social interaction, and is closely tied with power dynamics, social distance between the participants of a conversa- tion, and gender (Brown et al., 1987; Danescu- Niculescu-Mizil et al., 2013). It is also imperative to use the appropriate level of politeness for smooth communication in conversations (Coppock, 2005), organizational settings like emails (Peterson et al., 2011), memos, official documents, and many other settings. Notably, politeness has also been identi- fied as an interpersonal style which can be decou- pled from content (Kang and Hovy, 2019). Moti- vated by its central importance, in this paper we study the task of converting non-polite sentences to polite sentences while preserving the meaning. Prior work on text style transfer (Shen et al., 2017; Li et al., 2018; Prabhumoye et al., 2018; ∗ authors contributed equally to this work. Rao and Tetreault, 2018; Xu et al., 2012; Jham- tani et al., 2017) has not focused on politeness as a style transfer task, and we argue that defining it is cumbersome. While native speakers of a language and cohabitants of a region have a good working understanding of the phenomenon of politeness for everyday conversation, pinning it down as a definition is non-trivial (Meier, 1995). There are primarily two reasons for this complexity. First, as noted by (Brown et al., 1987), the phenomenon of politeness is rich and multifaceted. Second, polite- ness of a sentence depends on the culture, language, and social structure of both the speaker and the ad- dressed person. For instance, while using “please” in requests made to the closest friends is common amongst the native speakers of North American English, such an act would be considered awkward, if not rude, in the Arab culture (K´ad´ar and Mills, 2011). We …

Content truncated to 500 words