Multi-Task Neural Models for Translating Between Styles Within and Across Languages
Computation and Language
2018-06-13 v1
Abstract
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.
Cite
@article{arxiv.1806.04357,
title = {Multi-Task Neural Models for Translating Between Styles Within and Across Languages},
author = {Xing Niu and Sudha Rao and Marine Carpuat},
journal= {arXiv preprint arXiv:1806.04357},
year = {2018}
}
Comments
Accepted at the 27th International Conference on Computational Linguistics (COLING 2018)