Formality Style Transfer with Hybrid Textual Annotations

Abstract

Formality style transformation is the task of modifying the formality of a given sentence without changing its content. Its challenge is the lack of large-scale sentence-aligned parallel data. In this paper, we propose an omnivorous model that takes parallel data and formality-classified data jointly to alleviate the data sparsity issue. We empirically demonstrate the effectiveness of our approach by achieving the state-of-art performance on a recently proposed benchmark dataset of formality transfer. Furthermore, our model can be readily adapted to other unsupervised text style transfer tasks like unsupervised sentiment transfer and achieve competitive results on three widely recognized benchmarks.

References in corpus (3)

• Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study
• Structured Content Preservation for Unsupervised Text Style Transfer
• Improved Neural Text Attribute Transfer with Non-parallel Data

Cited by in corpus (6)

• Unsupervised Text Generation by Learning from Search
• From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey
• Contextual Text Style Transfer
• Parallel Data Augmentation for Formality Style Transfer
• Improving Formality Style Transfer with Context-Aware Rule Injection
• Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer