AESOP: Paraphrase Generation with Adaptive Syntactic Control

Jiao Sun, Xuezhe Ma, Nanyun Peng


Abstract
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.
Anthology ID:
2021.emnlp-main.420
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5176–5189
Language:
URL:
https://aclanthology.org/2021.emnlp-main.420
DOI:
10.18653/v1/2021.emnlp-main.420
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.420.pdf
Code
 pluslabnlp/aesop
Data
GLUE