Hybrid sub-word segmentation for handling long tail in morphologically rich low resource languages.

Sreeja Manghat Sreeram Manghat Tanja Schultz

Published in: ICASSP (2022)

Keyphrases

word segmentation
long tail
language independent
cross lingual
n gram
chinese text retrieval
pos tagging
online advertising
social media
machine translation
text classification
chinese word segmentation
chinese text
word level
recommendation systems
language modeling
part of speech
handwritten documents