Optimizing Word Segmentation for Downstream Task.

Tatsuya Hiraoka Sho Takase Kei Uchiumi Atsushi Keyaki Naoaki Okazaki

Published in: EMNLP (Findings) (2020)

Keyphrases

word segmentation
n gram
word recognition
chinese text
handwriting recognition
chinese word segmentation
text classification
language modeling
language independent
document analysis
pos tagging
cross lingual
machine learning
keywords
word level
chinese text retrieval