mlsanityData to 7 Oct 2026

Grammatical Error Correction Evaluation by Optimally Transporting Edit Representation

arXiv 2602.05419 ↗First posted 5 Feb 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Automatic evaluation in grammatical error correction (GEC) is crucial for selecting the best-performing systems. Currently, reference-based metrics are a popular choice, which basically measure the similarity between hypothesis and reference sentences. However, similarity measures based on embeddings, such as BERTScore, are often ineffective, since many words in the source sentences remain unchanged in both the hypothesis and the reference. This study focuses on edits specifically designed for GEC, i.e., ERRANT, and computes similarity measured over the edits from the source sentence. To this end, we propose edit vector, a representation for an edit, and introduce a new metric, UOT-ERRANT, which transports these edit vectors from hypothesis to reference using unbalanced optimal transport. Experiments with SEEDA meta-evaluation show that UOT-ERRANT improves evaluation performance, particularly in the +Fluency domain where many edits occur. Moreover, our method is highly interpretable because the transport plan can be interpreted as a soft edit alignment, making UOT-ERRANT a useful metric for both system ranking and analyzing GEC systems. Our code is available from https://github.com/gotutiyan/uot-errant.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 60 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

32 of 60 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  7. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  8. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  9. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  10. 2015Learning with a Wasserstein Losscited by 194
  11. 2020GECToR -- Grammatical Error Correction: Tag, Not Rewritecited by 177
  12. 2021A Simple Recipe for Multilingual Grammatical Error Correctioncited by 108
20 more
  1. 2016Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problemscited by 69
  2. 2019Hierarchical Optimal Transport for Document Representationcited by 53
  3. 2016Re-evaluating Automatic Metrics for Image Captioningcited by 45
  4. 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
  5. 2016Scaling Algorithms for Unbalanced Transport Problemscited by 36
  6. 2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognitioncited by 27
  7. 2016GLEU Without Tuningcited by 24
  8. 2020Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transportcited by 20
  9. 2022Revisiting Grammatical Error Correction Evaluation and Beyondcited by 18
  10. 2024GPT-3.5 for Grammatical Error Correctioncited by 18
  11. 2020Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analysescited by 16
  12. 2018Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplificationcited by 15
  13. 2022Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correctioncited by 12
  14. 2025gec-metrics: A Unified Library for Grammatical Error Correction Evaluationcited by 9
  15. 2024Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Modelscited by 8
  16. 2025Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?cited by 7
  17. 2023Unbalanced Optimal Transport for Unbalanced Word Alignmentcited by 6
  18. 2023CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correctioncited by 5
  19. 2024Revisiting Meta-evaluation for Grammatical Error Correctioncited by 3
  20. 2024Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correctioncited by 2

Built on by

Not cited yet.