Probabilistic Methods for a Japanese Syllable Cipher

This paper attacks a Japanese syllable-substitution cipher. We use a probabilistic, noisy-channel framework, exploiting various Japanese language models to drive the decipherment. We describe several innovations, including a new objective function for searching for the highestscoring decipherment. We include empirical studies of the relevant phenomena, and we give improved decipherment accuracy rates.

• Type: Conference
• Year: 2009
• Where: ICCPOL
• Authors: Sujith Ravi, Kevin Knight
• Keywords: Decipherment Accuracy Rates, ICCPOL 2009, Japanese Language Models, Japanese Syllable-substitution Cipher, Natural Language Processing