# Joint Copying and Restricted Generation for Paraphrase

arXiv: https://arxiv.org/abs/1611.09235 · HTML: https://mlsanity.com/paper/1611.09235/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2016.

## Built on by (most cited first, 17 of 17)

- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning](https://mlsanity.com/paper/2202.00535/) (2022)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [ConRPG: Paraphrase Generation using Contexts as Regularizer](https://mlsanity.com/paper/2109.00363/) (2021)
- [Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering](https://mlsanity.com/paper/2109.07095/) (2021)
- [ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://mlsanity.com/paper/2305.16585/) (2023)
- [Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning](https://mlsanity.com/paper/2103.12777/) (2021)
- [ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization](https://mlsanity.com/paper/2201.05313/) (2022)
- [LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training](https://mlsanity.com/paper/2401.04348/) (2024)
- [Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2211.00881/) (2022)
- [Fake News Detection After LLM Laundering: Measurement and Explanation](https://mlsanity.com/paper/2501.18649/) (2025)
- [Multi-Figurative Language Generation](https://mlsanity.com/paper/2209.01835/) (2022)
- [Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation](https://mlsanity.com/paper/2301.02275/) (2023)
- [Coherence and Diversity through Noise: Self-Supervised Paraphrase Generation via Structure-Aware Denoising](https://mlsanity.com/paper/2302.02780/) (2023)
- [Task-Oriented Paraphrase Analytics](https://mlsanity.com/paper/2403.17564/) (2024)
- [Paraphrase Generation as Unsupervised Machine Translation](https://mlsanity.com/paper/2109.02950/) (2021)
- [Fine-Grained Emotional Paraphrasing along Emotion Gradients](https://mlsanity.com/paper/2212.03297/) (2022)

## Abstract (arXiv)

Many natural language generation tasks, such as abstractive summarization and text simplification, are paraphrase-orientated. In these tasks, copying and rewriting are two main writing modes. Most previous sequence-to-sequence (Seq2Seq) models use a single decoder and neglect this fact. In this paper, we develop a novel Seq2Seq model to fuse a copying decoder and a restricted generative decoder. The copying decoder finds the position to be copied based on a typical attention model. The generative decoder produces words limited in the source-specific vocabulary. To combine the two decoders and determine the final output, we develop a predictor to predict the mode of copying or rewriting. This predictor can be guided by the actual writing mode in the training data. We conduct extensive experiments on two different paraphrase datasets. The result shows that our model outperforms the state-of-the-art approaches in terms of both informativeness and language quality.