quality_assurance · saas · workflow
GECToR: Grammarly's sequence-tagging 'tag, not rewrite' approach achieves state-of-the-art grammatical error correction with up to 10x faster inference
NMT-based GEC systems required large amounts of training data, generated inferences slowly, and could not explain what types of mistakes were made—making them better suited to academic research than real-world product deployment.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Token alignment preprocessing
Each source token is roughly aligned with one or more tokens from the target sequence by minimizing Levenshtein distance.
Tools used
GECToRBERT-like transformer
Outcome
GECToR achieved state-of-the-art F0.5 scores on standard GEC benchmarks and ran up to 10 times faster than NMT-based systems, with error coverage reaching 80% when g-transformations were included.
What failed first
The dominant NMT/seq2seq translation approach used encoder-decoder architecture where language generation was more complex than language understanding, resulting in slower inference and a black-box system with no explainability.
Results
Time saved0.40 sec
Volumeup to 10 times as fast
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
document aiquality inspectionfailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareaccuracy improvementcycle time reductiontechnical build writeupquality assuranceextract classify route