mlsanityData to 7 Oct 2026

Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering

arXiv 2109.07095 ↗First posted 15 Sep 2021cs.CL cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Paraphrase generation is an important task in natural language processing. Previous works focus on sentence-level paraphrase generation, while ignoring document-level paraphrase generation, which is a more challenging and valuable task. In this paper, we explore the task of document-level paraphrase generation for the first time and focus on the inter-sentence diversity by considering sentence rewriting and reordering. We propose CoRPG (Coherence Relationship guided Paraphrase Generation), which leverages graph GRU to encode the coherence relationship graph and get the coherence-aware representation for each sentence, which can be used for re-arranging the multiple (possibly modified) input sentences. We create a pseudo document-level paraphrase dataset for training CoRPG. Automatic evaluation results show CoRPG outperforms several strong baseline models on the BERTScore and diversity scores. Human evaluation also shows our model can generate document paraphrase with more diversity and semantic preservation.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

20 of 29 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2017Graph Attention Networkscited by 8,854
  4. 2016Layer Normalizationcited by 5,579
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  8. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  9. 2018Hierarchical Neural Story Generationcited by 1,182
  10. 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
  11. 2018Graph-to-Sequence Learning using Gated Graph Neural Networkscited by 61
  12. 2020Neural Syntactic Preordering for Controlled Paraphrase Generationcited by 56
8 more
  1. 2017A Deep Generative Framework for Paraphrase Generationcited by 54
  2. 2016Neural Paraphrase Generation with Stacked Residual LSTM Networkscited by 52
  3. 2017ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translationscited by 44
  4. 2019Decomposable Neural Paraphrase Generationcited by 30
  5. 2019Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learningcited by 29
  6. 2019A Unified Neural Coherence Modelcited by 19
  7. 2016Joint Copying and Restricted Generation for Paraphrasecited by 17
  8. 2020Rethinking Coherence Modeling: Synthetic vs. Downstream Taskscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 3; 2025: 1; 2026: 1.

10 papers.

  1. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  2. 2024No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choicescited by 47
  3. 2024Revisiting the Robustness of Watermarking to Paraphrasing Attackscited by 19
  4. 2025Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasingcited by 14
  5. 2022Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generationcited by 9
  6. 2022Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attentioncited by 3
  7. 2023Context-Aware Document Simplificationcited by 3
  8. 2023Is it Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Modelscited by 3
  9. 2024Linguistically-Controlled Paraphrase Generationcited by 1
  10. 2026Robust LLM Watermarking with Minimal Semantic Distortion for IP Protectioncited by 1