Cost-benefit Analysis of Two-Stage Conditional Random Fields based English-to-Chinese Machine Transliteration
Chan-Hung Kuo, Shih‐Hung Liu, Mike Tian-Jian Jiang, Cheng‐Wei Lee, Wen‐Lian Hsu · 2012
This work presents an English-to-Chinese (E2C) machine transliteration system based on two-stage conditional random fields (CRF) models with accessor variety (AV) as an additional feature to approximate local context of the source language. Experiment results show that two-stage CRF method outperforms the one-stage opponent since the former costs less to encode more features and finer grained labels than the latter. 1