Mining Transliterations from Web Query Results: An Incremental Approach
Jin‐Shea Kuo, Haizhou Li, Chih‐Lung Lin · 2008
We study an adaptive learning framework for phonetic similarity modeling (PSM) that supports the automatic acquisition of trans-literations by exploiting minimum prior knowledge about machine transliteration to mine transliterations incrementally from the live Web. We formulate an incremental learning strategy for the framework based on Bayesian theory for PSM adaptation. The idea of incremental learning is to bene-fit from the continuously developing his-tory to update a static model towards the in-tended reality. In this way, the learning process refines the PSM incrementally while constructing a transliteration lexicon at the same time on a development corpus. We further demonstrate that the proposed learning framework is reliably effective in mining live transliterations from Web query results. 1