# Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations

arXiv: https://arxiv.org/abs/2211.00881 · HTML: https://mlsanity.com/paper/2211.00881/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 20 of 20)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://mlsanity.com/paper/1804.06059/) (2018)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Generating Sentences from Disentangled Syntactic and Semantic Spaces](https://mlsanity.com/paper/1907.05789/) (2019)
- [Neural AMR: Sequence-to-Sequence Models for Parsing and Generation](https://mlsanity.com/paper/1704.08381/) (2017)
- [Neural Syntactic Preordering for Controlled Paraphrase Generation](https://mlsanity.com/paper/2005.02013/) (2020)
- [A Deep Generative Framework for Paraphrase Generation](https://mlsanity.com/paper/1709.05074/) (2017)
- [AMR Parsing via Graph-Sequence Iterative Inference](https://mlsanity.com/paper/2004.05572/) (2020)
- [Syntax-guided Controlled Generation of Paraphrases](https://mlsanity.com/paper/2005.08417/) (2020)
- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [Controllable Paraphrase Generation with a Syntactic Exemplar](https://mlsanity.com/paper/1906.00565/) (2019)
- [Paraphrase Augmented Task-Oriented Dialog Generation](https://mlsanity.com/paper/2004.07462/) (2020)
- [Paraphrase Generation with Latent Bag of Words](https://mlsanity.com/paper/2001.01941/) (2020)
- [Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning](https://mlsanity.com/paper/2202.00535/) (2022)
- [Semantic Representation for Dialogue Modeling](https://mlsanity.com/paper/2105.10188/) (2021)
- [HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge](https://mlsanity.com/paper/2109.05097/) (2021)
- [Unsupervised Paraphrasing without Translation](https://mlsanity.com/paper/1905.12752/) (2019)
- [Syntax-Infused Variational Autoencoder for Text Generation](https://mlsanity.com/paper/1906.02181/) (2019)
- [Joint Copying and Restricted Generation for Paraphrase](https://mlsanity.com/paper/1611.09235/) (2016)
- [Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach](https://mlsanity.com/paper/2109.01862/) (2021)

## Built on by (most cited first, 4 of 4)

- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://mlsanity.com/paper/2305.16585/) (2023)
- [PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation](https://mlsanity.com/paper/2305.16701/) (2023)
- [Linguistically-Controlled Paraphrase Generation](https://mlsanity.com/paper/2410.24199/) (2024)

## Abstract (arXiv)

Syntactically controlled paraphrase generation has become an emerging research direction in recent years. Most existing approaches require annotated paraphrase pairs for training and are thus costly to extend to new domains. Unsupervised approaches, on the other hand, do not need paraphrase pairs but suffer from relatively poor performance in terms of syntactic control and quality of generated paraphrases. In this paper, we demonstrate that leveraging Abstract Meaning Representations (AMR) can greatly improve the performance of unsupervised syntactically controlled paraphrase generation. Our proposed model, AMR-enhanced Paraphrase Generator (AMRPG), separately encodes the AMR graph and the constituency parse of the input sentence into two disentangled semantic and syntactic embeddings. A decoder is then learned to reconstruct the input sentence from the semantic and syntactic embeddings. Our experiments show that AMRPG generates more accurate syntactically controlled paraphrases, both quantitatively and qualitatively, compared to the existing unsupervised approaches. We also demonstrate that the paraphrases generated by AMRPG can be used for data augmentation to improve the robustness of NLP models.