An Advanced Review of Hybrid Machine Translation (HMT)
Haoyuan Xuan, W. Li, Grace Tang · Procedia Engineering · 2012
Machine translation (MT) has been the milestone of language understanding, ultimately seeking to provide high quality translation between pairs of languages, which is the genesis of natural language processing (NLP). Hybrid machine translation (HMT) is integrates the core of existing methods, including rule-based MT, statistical-based MT, and example-based MT, which makes up the deficiencies of individual MT method. This paper discusses the typical couplings of translation methods, and pointed out the advantages and deficiencies. Besides these combinations, architecture expansion approaches for system optimization are introduced. This paper also reviews the technologies employed for system evaluation.