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.
Title resolution pending
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
Learned heads improve intrinsic head prediction but fail to deliver consistent punctuation-sensitive parsing gains after binarization and debinarization.
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.
-
Better heads do not guarantee better binarized constituency parsing
Learned heads improve intrinsic head prediction but fail to deliver consistent punctuation-sensitive parsing gains after binarization and debinarization.