Introduces an alignment projection method for recovering word boundaries in noisy Chinese text, plus two new evaluation benchmarks showing it corrects over-segmentation better than direct segmentation.
MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Refines Korean GEC annotation by reconstructing NIKL targets under morphological rules, converting to m2 edits, defining a Korean ERRANT scheme, and adding a second reference to KoLLA for multi-reference evaluation.
citing papers explorer
-
Chinese Word Boundary Recovery through Character Alignment Projection
Introduces an alignment projection method for recovering word boundaries in noisy Chinese text, plus two new evaluation benchmarks showing it corrects over-segmentation better than direct segmentation.
-
Refining Word-Based Grammatical Error Annotation for L2 Korean
Refines Korean GEC annotation by reconstructing NIKL targets under morphological rules, converting to m2 edits, defining a Korean ERRANT scheme, and adding a second reference to KoLLA for multi-reference evaluation.