Paper: Unsupervised Analysis For Decipherment Problems

ACL ID P06-2065
Title Unsupervised Analysis For Decipherment Problems
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

We study a number of natural language deci- pherment problems using unsupervised learn- ing. These include letter substitution ciphers, character code conversion, phonetic decipher- ment, and word-based ciphers with relevance to machine translation. Straightforward unsu- pervised learning techniques most often fail on the rst try, so we describe techniques for un- derstanding errors and signi cantly increasing performance.