mlsanityData to 7 Oct 2026

Encode, Tag, Realize: High-Precision Text Editing

arXiv 1909.01187 ↗First posted 3 Sep 2019cs.CLcited by 99

Not on the map. Why?

Abstract (arXiv)

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase before the token. To predict the edit operations, we propose a novel model, which combines a BERT encoder with an autoregressive Transformer decoder. This approach is evaluated on English text on four tasks: sentence fusion, sentence splitting, abstractive summarization, and grammar correction. LaserTagger achieves new state-of-the-art results on three of these tasks, performs comparably to a set of strong seq2seq baselines with a large number of training examples, and outperforms them when the number of examples is limited. Furthermore, we show that at inference time tagging can be more than two orders of magnitude faster than comparable seq2seq models, making it more attractive for running in a live environment.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 29; 2023: 30; 2024: 10; 2025: 6; 2026: 8.

99 papers.

Sort:

By area:

  1. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  2. 2022Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generationcited by 169
  3. 2021A Simple Recipe for Multilingual Grammatical Error Correctioncited by 108
  4. 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
  5. 2022Understanding Iterative Revision from Human-Written Textcited by 56
  6. 2021Instantaneous Grammatical Error Correction with Shallow Aggressive Decodingcited by 53
  7. 2022Grammatical Error Correction: A Survey of the State of the Artcited by 43
  8. 2022DiffusER: Discrete Diffusion via Edit-based Reconstructioncited by 41
  9. 2021LEWIS: Levenshtein Editing for Unsupervised Text Style Transfercited by 40
  10. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  11. 2022EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Startcited by 35
  12. 2023ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviewscited by 34
38 more
  1. 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
  2. 2022MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correctioncited by 33
  3. 2021Focus Attention: Promoting Faithfulness and Diversity in Summarizationcited by 30
  4. 2022Learning to Model Editing Processescited by 30
  5. 2022EditEval: An Instruction-Based Benchmark for Text Improvementscited by 30
  6. 2021Text Simplification by Taggingcited by 27
  7. 2023Second Thoughts are Best: Learning to Re-Align With Human Values from Text Editscited by 27
  8. 2022Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correctioncited by 25
  9. 2021Learning to Complete Code with Sketchescited by 23
  10. 2023Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigationcited by 22
  11. 2022Text Generation with Text-Editing Modelscited by 21
  12. 2022An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Modelscited by 20
  13. 2022Improving Iterative Text Revision by Learning Where to Edit from Other Revision Taskscited by 20
  14. 2021Idiomatic Expression Identification using Semantic Compatibilitycited by 19
  15. 2024GPT-3.5 for Grammatical Error Correctioncited by 18
  16. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  17. 2021Learning Structural Edits via Incremental Tree Transformationscited by 16
  18. 2023Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Textscited by 16
  19. 2022Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generationcited by 15
  20. 2021A New Approach to Overgenerating and Scoring Abstractive Summariescited by 13
  21. 2022FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correctioncited by 13
  22. 2022Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correctioncited by 12
  23. 2023SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pagescited by 12
  24. 2023Beyond English: Evaluating LLMs for Arabic Grammatical Error Correctioncited by 12
  25. 2021Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correctioncited by 11
  26. 2021AgreeSum: Agreement-Oriented Multi-Document Summarizationcited by 10
  27. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  28. 2022Type-Driven Multi-Turn Corrections for Grammatical Error Correctioncited by 9
  29. 2023NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Textscited by 9
  30. 2025Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Studycited by 9
  31. 2022Dynamic Planning in Open-Ended Dialogue using Reinforcement Learningcited by 8
  32. 2023Non-autoregressive Text Editing with Copy-aware Latent Alignmentscited by 8
  33. 2022Explicit Image Caption Editingcited by 7
  34. 2022From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correctioncited by 7
  35. 2023Exploring the Landscape of Natural Language Processing Researchcited by 7
  36. 2023Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correctioncited by 7
  37. 2024Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checkingcited by 7
  38. 2022ASR Error Correction with Constrained Decoding on Operation Predictioncited by 6

50 most cited of 99 All 99 (JSON)