%0 Conference Proceedings %T AESOP: Paraphrase Generation with Adaptive Syntactic Control %A Sun, Jiao %A Ma, Xuezhe %A Peng, Nanyun %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F sun-etal-2021-aesop %X We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases. Our model, AESOP, leverages a pretrained language model and adds deliberately chosen syntactical control via a retrieval-based selection module to generate fluent paraphrases. Experiments show that AESOP achieves state-of-the-art performances on semantic preservation and syntactic conformation on two benchmark datasets with ground-truth syntactic control from human-annotated exemplars. Moreover, with the retrieval-based target syntax selection module, AESOP generates paraphrases with even better qualities than the current best model using human-annotated target syntactic parses according to human evaluation. We further demonstrate the effectiveness of AESOP to improve classification models’ robustness to syntactic perturbation by data augmentation on two GLUE tasks. %R 10.18653/v1/2021.emnlp-main.420 %U https://aclanthology.org/2021.emnlp-main.420 %U https://doi.org/10.18653/v1/2021.emnlp-main.420 %P 5176-5189