# Controllable Paraphrase Generation with a Syntactic Exemplar

arXiv: https://arxiv.org/abs/1906.00565 · HTML: https://mlsanity.com/paper/1906.00565/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 30 of 44)

- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Tailor: Generating and Perturbing Text with Semantic Controls](https://mlsanity.com/paper/2107.07150/) (2021)
- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness](https://mlsanity.com/paper/2305.12947/) (2023)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [Quality Controlled Paraphrase Generation](https://mlsanity.com/paper/2203.10940/) (2022)
- [Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing](https://mlsanity.com/paper/2305.16635/) (2023)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning](https://mlsanity.com/paper/2202.00535/) (2022)
- [CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation](https://mlsanity.com/paper/2210.04873/) (2022)
- [Factorising Meaning and Form for Intent-Preserving Paraphrasing](https://mlsanity.com/paper/2105.15053/) (2021)
- [Hierarchical Sketch Induction for Paraphrase Generation](https://mlsanity.com/paper/2203.03463/) (2022)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges](https://mlsanity.com/paper/2405.15604/) (2024)
- [Improving Formality Style Transfer with Context-Aware Rule Injection](https://mlsanity.com/paper/2106.00210/) (2021)
- [ConRPG: Paraphrase Generation using Contexts as Regularizer](https://mlsanity.com/paper/2109.00363/) (2021)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation](https://mlsanity.com/paper/2304.11501/) (2023)
- [Monotonic Paraphrasing Improves Generalization of Language Model Prompting](https://mlsanity.com/paper/2403.16038/) (2024)
- [Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication](https://mlsanity.com/paper/2106.11791/) (2021)
- [Improving Large-scale Paraphrase Acquisition and Generation](https://mlsanity.com/paper/2210.03235/) (2022)
- [Expository Text Generation: Imitate, Retrieve, Paraphrase](https://mlsanity.com/paper/2305.03276/) (2023)
- [Explicit Syntactic Guidance for Neural Text Generation](https://mlsanity.com/paper/2306.11485/) (2023)
- [Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation](https://mlsanity.com/paper/2109.01484/) (2021)
- [Principled Paraphrase Generation with Parallel Corpora](https://mlsanity.com/paper/2205.12213/) (2022)
- [Data-to-text Generation by Splicing Together Nearest Neighbors](https://mlsanity.com/paper/2101.08248/) (2021)
- [Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2211.00881/) (2022)

## Abstract (arXiv)

Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel task, where the syntax of a generated sentence is controlled rather by a sentential exemplar. To evaluate quantitatively with standard metrics, we create a novel dataset with human annotations. We also develop a variational model with a neural module specifically designed for capturing syntactic knowledge and several multitask training objectives to promote disentangled representation learning. Empirically, the proposed model is observed to achieve improvements over baselines and learn to capture desirable characteristics.