Artificial word insertions and deletions in news text, used as self-supervised pretraining tasks, transfer to human-annotated disfluency detection and cut the labeled-data requirement to 1,000 sentences.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Task Self-Supervised Learning for Disfluency Detection
Artificial word insertions and deletions in news text, used as self-supervised pretraining tasks, transfer to human-annotated disfluency detection and cut the labeled-data requirement to 1,000 sentences.