Statistical Transliteration for Cross Langauge Information Retrieval using HMM alignment and CRF
Surya Ganesh, Sree Harsha, Prasad Pingali, Vasudeva Varma · 2008
In this paper we present a statistical translit-eration technique that is language indepen-dent. This technique uses Hidden Markov Model (HMM) alignment and Conditional Random Fields (CRF), a discriminative model. HMM alignment maximizes the probability of the observed (source, target) word pairs using the expectation maximiza-tion algorithm and then the character level alignments (n-gram) are set to maximum posterior predictions of the model. CRF has efficient training and decoding processes which is conditioned on both source and target languages and produces globally op-timal solutions. We apply this technique for Hindi-English transliteration task. The results show that our technique perfoms better than the existing transliteration sys-tem which uses HMM alignment and con-ditional probabilities derived from counting the alignments. 1