TY - GEN
T1 - Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer
AU - Gong, Hongyu
AU - Song, Linfeng
AU - Bhat, Suma
N1 - This work was supported by the IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR)-a research collaboration as part of the IBM AI Horizons Network. We would like to thank the anonymous reviewers for their constructive comments and suggestions. We also thank Raghavendra Bhat for data annotations.
PY - 2020
Y1 - 2020
N2 - Text style transfer aims to change an input sentence to an output sentence by changing its text style while preserving the content. Previous efforts on unsupervised text style transfer only use the surface features of words and sentences. As a result, the transferred sentences may either have inaccurate or missing information compared to the inputs. We address this issue by explicitly enriching the inputs via syntactic and semantic structures, from which richer features are then extracted to better capture the original information. Experiments on two text-style-transfer tasks show that our approach improves the content preservation of a strong unsupervised baseline model thereby demonstrating improved transfer performance.
AB - Text style transfer aims to change an input sentence to an output sentence by changing its text style while preserving the content. Previous efforts on unsupervised text style transfer only use the surface features of words and sentences. As a result, the transferred sentences may either have inaccurate or missing information compared to the inputs. We address this issue by explicitly enriching the inputs via syntactic and semantic structures, from which richer features are then extracted to better capture the original information. Experiments on two text-style-transfer tasks show that our approach improves the content preservation of a strong unsupervised baseline model thereby demonstrating improved transfer performance.
UR - https://www.scopus.com/pages/publications/85118913258
UR - https://www.scopus.com/pages/publications/85118913258#tab=citedBy
U2 - 10.18653/v1/2020.inlg-1.17
DO - 10.18653/v1/2020.inlg-1.17
M3 - Conference contribution
AN - SCOPUS:85118913258
T3 - INLG 2020 - 13th International Conference on Natural Language Generation, Proceedings
SP - 113
EP - 119
BT - INLG 2020 - 13th International Conference on Natural Language Generation, Proceedings
A2 - Davis, Brian
A2 - Graham, Yvette
A2 - Kelleher, John
A2 - Sripada, Yaji
PB - Association for Computational Linguistics (ACL)
T2 - 13th International Conference on Natural Language Generation, INLG 2020
Y2 - 15 December 2020 through 18 December 2020
ER -