Politeness Transfer: A Tag and Generate Approach

Tag and Generate Approach:The tagger infers the interpretable style free sentence z(xi).

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.

Politeness task

Input: What happened to my personal station?
Output: Could you please let me know what happened to my personal station?
Politeness Strategy: could and would are counterfactual forms which are polite.
Input: Yes, go ahead and remove it.
Output: Yes, we can go ahead and remove it.
Politeness Strategy: 1st person plural form creates a sense that the burden of the request is shared by speaker and addressee.
Input: Not yet-i’ll try this weekend.
Output: Sorry, not yet-i’ll try to make sure this week.
Politeness Strategy: Apologizing deflects the social threat of the request by attuning to the imposition itself.
Input: Please check on metromedia energy.
Output: Please check on metromedia energy, thanks.
Politeness Strategy: Mitigating please start.