AESOP: Paraphrase Generation with Adaptive Syntactic Control
By Jiao Sun, Xuezhe Ma, Nanyun Peng. 2021
52 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Matt Gardner
- Matthew E. Peters
- Hao Peng
- Tongshuang Sherry Wu
- Alexis Ross
- Mohit Bansal
- Noah A. Smith
- Luke S. Zettlemoyer
In Computer Vision and Pattern Recognition
- Matthew E. Peters
- Matt Gardner
- Hao Peng
- Alexis Ross
- Tongshuang Sherry Wu
- Yonatan Belinkov
- Hannaneh Hajishirzi
- Jonathan Berant
In Natural Language Processing
- Matt Gardner
- Matthew E. Peters
- Tongshuang Sherry Wu
- Hao Peng
- Alexis Ross
- Mohit Bansal
- Luke S. Zettlemoyer
- Jonathan Berant
Citations in the corpus
- Tailor: Generating and Perturbing Text with Semantic Controls (2021, background): “Recent works incorporating syntactic structures for paraphrasing (Iyyer et al., 2018; Chen et al., 2019; Bao et al., 2019; Kumar et al., 2020; Sun et al., 2021; Huang and Chang, 2021) or discrete semantic signatures for diverse generation (Weir et al., 2020) are similar to T ailor in their…”