Multi-Task Neural Models for Translating Between Styles Within and Across Languages
This work addresses the challenge of controlling linguistic style in natural language generation for applications like translation and text adaptation, though it builds incrementally on existing multi-task learning approaches.
The paper tackles the problem of generating text with appropriate formality levels by jointly addressing monolingual formality transfer and formality-sensitive machine translation using multi-task learning. The models achieve state-of-the-art performance for formality transfer and enable formality-sensitive translation without explicit style-annotated translation data.
Generating natural language requires conveying content in an appropriate style. We explore two related tasks on generating text of varying formality: monolingual formality transfer and formality-sensitive machine translation. We propose to solve these tasks jointly using multi-task learning, and show that our models achieve state-of-the-art performance for formality transfer and are able to perform formality-sensitive translation without being explicitly trained on style-annotated translation examples.