mlsanityData to 14 Oct 2026

BLEU is Not Suitable for the Evaluation of Text Simplification

arXiv 1810.05995 ↗First posted 14 Oct 2018cs.CLcited by 78

Not on the map. Why?

Abstract (arXiv)

BLEU is widely considered to be an informative metric for text-to-text generation, including Text Simplification (TS). TS includes both lexical and structural aspects. In this paper we show that BLEU is not suitable for the evaluation of sentence splitting, the major structural simplification operation. We manually compiled a sentence splitting gold standard corpus containing multiple structural paraphrases, and performed a correlation analysis with human judgments. We find low or no correlation between BLEU and the grammaticality and meaning preservation parameters where sentence splitting is involved. Moreover, BLEU often negatively correlates with simplicity, essentially penalizing simpler sentences.

Key facts. Cited by 78 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 11; 2023: 22; 2024: 15; 2025: 11; 2026: 8.

78 papers.

Sort:

By area:

  1. 2021A Comprehensive Assessment of Dialog Evaluation Metricscited by 90
  2. 2024LLM-based NLG Evaluation: Current Status and Challengescited by 73
  3. 2023Efficient Benchmarking of Language Modelscited by 71
  4. 2022GEMv2: Multilingual NLG Benchmarking in a Single Line of Codecited by 36
  5. 2021Text Simplification by Taggingcited by 27
  6. 2021Document-Level Text Simplification: Dataset, Criteria and Baselinecited by 27
  7. 2023Revisiting non-English Text Simplification: A Unified Multilingual Benchmarkcited by 27
  8. 2022StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoningcited by 21
  9. 2023Learning to Simulate Natural Language Feedback for Interactive Semantic Parsingcited by 19
  10. 2024Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretabilitycited by 19
  11. 2021BiSECT: Learning to Split and Rephrase Sentences with Bitextscited by 18
  12. 2021Rethinking Automatic Evaluation in Sentence Simplificationcited by 17
38 more
  1. 2024What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluationcited by 17
  2. 2023Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehensioncited by 16
  3. 2023Sentence Simplification via Large Language Modelscited by 15
  4. 2023APPLS: Evaluating Evaluation Metrics for Plain Language Summarizationcited by 15
  5. 2023Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSAcited by 15
  6. 2021An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languagescited by 14
  7. 2023DEPLAIN: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplificationcited by 14
  8. 2023X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agentscited by 13
  9. 2024A Comparative Study of Quality Evaluation Methods for Text Summarizationcited by 13
  10. 2023SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pagescited by 12
  11. 2023Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying Referencescited by 11
  12. 2021Lost in Interpreting: Speech Translation from Source or Interpreter?cited by 10
  13. 2023Teaching the Pre-trained Model to Generate Simple Texts for Text Simplificationcited by 10
  14. 2023Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisationscited by 9
  15. 2021Investigating Text Simplification Evaluationcited by 5
  16. 2023Exploiting Summarization Data to Help Text Simplificationcited by 5
  17. 2024Enabling Scalable Evaluation of Bias Patterns in Medical LLMscited by 5
  18. 2025Enterprise Large Language Model Evaluation Benchmarkcited by 5
  19. 2021Towards more patient friendly clinical notes through language models and ontologiescited by 4
  20. 2022WDV: A Broad Data Verbalisation Dataset Built from Wikidatacited by 4
  21. 2023A New Dataset and Empirical Study for Sentence Simplification in Chinesecited by 4
  22. 2024German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Datacited by 4
  23. 2024An In-depth Evaluation of Large Language Models in Sentence Simplification with Error-based Human Assessmentcited by 4
  24. 2024Measuring Bias in a Ranked List using Term-based Representationscited by 4
  25. 2025Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplificationcited by 4
  26. 2025Past, Present, and Future of Bug Tracking in the Generative AI Eracited by 4
  27. 2022MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplificationcited by 3
  28. 2022Social Biases in Automatic Evaluation Metrics for NLGcited by 3
  29. 2022Sentence-level Feedback Generation for English Language Learners: Does Data Augmentation Help?cited by 3
  30. 2023SimpLex: a lexical text simplification architecturecited by 3
  31. 2023HonestBait: Forward References for Attractive but Faithful Headline Generationcited by 3
  32. 2023Metric-Based In-context Learning: A Case Study in Text Simplificationcited by 3
  33. 2024REFeREE: A REference-FREE Model-Based Metric for Text Simplificationcited by 3
  34. 2024JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensemblescited by 3
  35. 2024SciGisPy: a Novel Metric for Biomedical Text Simplification via Gist Inference Scorecited by 3
  36. 2024SiTSE: Sinhala Text Simplification Dataset and Evaluationcited by 3
  37. 2026Cross-Lingual LLM-Judge Transfer via Evaluation Decompositioncited by 3
  38. 2022Cognitive Simplification Operations Improve Text Simplificationcited by 2

50 most cited of 78 All 78 (JSON)