A Study of BPE-based Language Modeling for Open Vocabulary Latin Language OCR.

Wenping Hu Yikang Luo Ji Meng Zifei Qian Qiang Huo

Published in: ICFHR (2020)

Keyphrases

language modeling
language model
optical character recognition
information retrieval
query expansion
probabilistic model
retrieval model
statistical language models
machine learning
feature selection
text mining
n gram
character recognition
comparable corpora