mlsanityData to 7 Oct 2026

Neural CRF Model for Sentence Alignment in Text Simplification

arXiv 2005.02324 ↗First posted 5 May 2020cs.CLcited by 106

Not on the map. Why?

Abstract (arXiv)

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity. Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1. We apply our CRF aligner to construct two new text simplification datasets, Newsela-Auto and Wiki-Auto, which are much larger and of better quality compared to the existing datasets. A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 21; 2023: 35; 2024: 22; 2025: 11; 2026: 5.

106 papers.

Sort:

By area:

  1. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
  2. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  3. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  4. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  5. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  6. 2022Fine-tuned Language Models are Continual Learnerscited by 152
  7. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  8. 2023Unified Demonstration Retriever for In-Context Learningcited by 141
  9. 2021The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generationcited by 96
  10. 2024Revisiting Catastrophic Forgetting in Large Language Model Tuningcited by 93
  11. 2023Exploring the Benefits of Training Expert Language Models over Instruction Tuningcited by 80
  12. 2023CoEdIT: Text Editing by Task-Specific Instruction Tuningcited by 67
38 more
  1. 2022SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformerscited by 63
  2. 2023TESS: Text-to-Text Self-Conditioned Simplex Diffusioncited by 63
  3. 2022LENS: A Learnable Evaluation Metric for Text Simplificationcited by 54
  4. 2023Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Taskscited by 53
  5. 2023DINOISER: Diffused Conditional Sequence Learning by Manipulating Noisescited by 50
  6. 2023AttentionViz: A Global View of Transformer Attentioncited by 50
  7. 2022Empowering Diffusion Models on the Embedding Space for Text Generationcited by 40
  8. 2023Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?cited by 39
  9. 2022GEMv2: Multilingual NLG Benchmarking in a Single Line of Codecited by 36
  10. 2021Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learningcited by 35
  11. 2023ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviewscited by 34
  12. 2023BLESS: Benchmarking Large Language Models on Sentence Simplificationcited by 34
  13. 2022CEFR-Based Sentence Difficulty Annotation and Assessmentcited by 28
  14. 2021Document-Level Text Simplification: Dataset, Criteria and Baselinecited by 27
  15. 2023Revisiting non-English Text Simplification: A Unified Multilingual Benchmarkcited by 27
  16. 2022arXivEdits: Understanding the Human Revision Process in Scientific Writingcited by 26
  17. 2024TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodingscited by 22
  18. 2023SPEC5G: A Dataset for 5G Cellular Network Protocol Analysiscited by 20
  19. 2022Neural Pipeline for Zero-Shot Data-to-Text Generationcited by 19
  20. 2022A Dataset for Plain Language Adaptation of Biomedical Abstractscited by 19
  21. 2025DLM-One: Diffusion Language Models for One-Step Sequence Generationcited by 19
  22. 2021Automatic Construction of Evaluation Suites for Natural Language Generation Datasetscited by 18
  23. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  24. 2022MVP: Multi-task Supervised Pre-training for Natural Language Generationcited by 16
  25. 2023Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Textscited by 16
  26. 2023Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehensioncited by 16
  27. 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
  28. 2024Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotationcited by 16
  29. 2021Neural semi-Markov CRF for Monolingual Word Alignmentcited by 15
  30. 2022Klexikon: A German Dataset for Joint Summarization and Simplificationcited by 15
  31. 2023Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSAcited by 15
  32. 2023DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplificationcited by 14
  33. 2023Multilingual Simplification of Medical Textscited by 13
  34. 2023Deliberate then Generate: Enhanced Prompting Framework for Text Generationcited by 13
  35. 2024mEdIT: Multilingual Text Editing via Instruction Tuningcited by 13
  36. 2024Improving Minimum Bayes Risk Decoding with Multi-Promptcited by 13
  37. 2022Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Expertscited by 12
  38. 2023SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pagescited by 12

50 most cited of 106 All 106 (JSON)