Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings
Kalpesh Krishna, Deepak Nathani, Xavier García, Bidisha Samanta, Partha Talukdar
2022Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)14 citationsDOIOpen Access PDF
Abstract
Style transfer is the task of rewriting a sentence into a target style while approximately preserving content. While most prior literature assumes access to a large style-labelled corpus, recent work In this work, we study a relevant low-resource setting: style transfer for languages where no style-labelled corpora are available. We notice that existing few-shot methods perform this task poorly, often copying inputs verbatim.
Topics & Concepts
Computer scienceNatural language processingFormalityArtificial intelligenceSentenceStyle (visual arts)Task (project management)Transfer (computing)Resource (disambiguation)LinguisticsParallel computingEconomicsArchaeologyComputer networkPhilosophyManagementHistoryTopic ModelingNatural Language Processing TechniquesText Readability and Simplification