Chiao-Wen Li - Academia.edu (original) (raw)

Chiao-Wen Li

Related Authors

Sven Behnke

Sven Behnke

Rheinische Friedrich-Wilhelms-Universität Bonn

Maria  Milosavljevic

Gloria  Corpas Pastor

MARIA STASIMIOTI

Vilelmini Sosoni

Sungchang Lee

Uploads

Papers by Chiao-Wen Li

Research paper thumbnail of Chinese Spelling Check based on Neural Machine Translation

We present a method for Chinese spelling check that automatically learns to correct a sentence wi... more We present a method for Chinese spelling check that automatically learns to correct a sentence with potential spelling errors. In our approach, a character-based neural machine translation (NMT) model is trained to translate the potentially misspelled sentence into correct one, using right-and-wrong sentence pairs from newspaper edit logs and artificially generated data. The method involves extracting sentences contain edit of spelling correction from edit logs, using commonly confused right-and-wrong word pairs to generate artificial right-and-wrong sentence pairs in order to expand our training data , and training the NMT model. The evaluation on the United Daily News (UDN) Edit Logs and SIGHAN-7 Shared Task shows that adding artificial error data can significantly improve the performance of Chinese spelling check system.

Research paper thumbnail of Chinese Spelling Check based on Neural Machine Translation

We present a method for Chinese spelling check that automatically learns to correct a sentence wi... more We present a method for Chinese spelling check that automatically learns to correct a sentence with potential spelling errors. In our approach, a character-based neural machine translation (NMT) model is trained to translate the potentially misspelled sentence into correct one, using right-and-wrong sentence pairs from newspaper edit logs and artificially generated data. The method involves extracting sentences contain edit of spelling correction from edit logs, using commonly confused right-and-wrong word pairs to generate artificial right-and-wrong sentence pairs in order to expand our training data , and training the NMT model. The evaluation on the United Daily News (UDN) Edit Logs and SIGHAN-7 Shared Task shows that adding artificial error data can significantly improve the performance of Chinese spelling check system.

Log In