mlsanityData to 7 Oct 2026

Sentence-Permuted Paragraph Generation

arXiv 2104.07228 ↗First posted 15 Apr 2021cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Generating paragraphs of diverse contents is important in many applications. Existing generation models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order. Our idea is permuting the sentence orders to improve the content diversity of multi-sentence paragraph. We propose a novel framework PermGen whose objective is to maximize the expected log-likelihood of output paragraph distributions with respect to all possible sentence orders. PermGen uses hierarchical positional embedding and designs new procedures for training, decoding, and candidate ranking in the sentence-permuted generation. Experiments on three paragraph generation benchmarks demonstrate PermGen generates more diverse outputs with a higher quality than existing models.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

39 of 50 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  8. 2018Hierarchical Neural Story Generationcited by 1,182
  9. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  10. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  11. 2017Non-Autoregressive Neural Machine Translationcited by 457
  12. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
27 more
  1. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
  2. 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 232
  3. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  4. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  5. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  6. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
  7. 2019Text Generation from Knowledge Graphs with Graph Transformerscited by 122
  8. 2020A Survey of Knowledge-Enhanced Text Generationcited by 119
  9. 2018Generating Informative and Diverse Conversational Responses via Adversarial Information Maximizationcited by 114
  10. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  11. 2017Long Text Generation via Adversarial Training with Leaked Informationcited by 100
  12. 2018Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputscited by 96
  13. 2019Comparison of Diverse Decoding Methods from Conditional Language Modelscited by 78
  14. 2019Mixture Models for Diverse Machine Translation: Tricks of the Tradecited by 77
  15. 2018Story Ending Generation with Incremental Encoding and Commonsense Knowledgecited by 60
  16. 2017A Deep Generative Framework for Paraphrase Generationcited by 54
  17. 2020Blank Language Modelscited by 43
  18. 2018Toward Diverse Text Generation with Inverse Reinforcement Learningcited by 41
  19. 2018Non-Autoregressive Neural Machine Translation with Enhanced Decoder Inputcited by 39
  20. 2019PaperRobot: Incremental Draft Generation of Scientific Ideascited by 37
  21. 2020A Study of Non-autoregressive Model for Sequence Generationcited by 31
  22. 2019Mixture Content Selection for Diverse Sequence Generationcited by 27
  23. 2019Sentence-Level Content Planning and Style Specification for Neural Text Generationcited by 23
  24. 2020POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-trainingcited by 10
  25. 2020Injecting Entity Types into Entity-Guided Text Generationcited by 7
  26. 2020Target Conditioning for One-to-Many Generationcited by 6
  27. 2020Graph-based Multi-hop Reasoning for Long Text Generationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 2.

4 papers.

  1. 2022Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Expertscited by 19
  2. 2023Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgmentscited by 2
  3. 2026Labeled Incidence Structures for Native Transformer Modeling of Text, Knowledge Graphs, and Hypergraphscited by 0
  4. 2026Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structurecited by 0