Ruslan Salakhutdinov, Graham Neubig, Yiming Yang, Aman Madaan, Amrith Setlur, Alan Black, Shrimai Prabhumoye, Tanmay Parekh, Barnabas Poczos
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 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 same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.14257")
get_code_for_paper("2004.14257")
have("2004.14257")
Connect an agent — have() is free.