作者: Sittichai Jiampojamarn , Grzegorz Kondrak , Shane Bergsma , Qing Dou , Kenneth Dwyer
DOI:
关键词: Artificial intelligence 、 Machine learning 、 Data mining 、 Transliteration 、 Computer science 、 Discriminative model 、 Range (mathematics)
摘要: We present DirecTL+: an online discriminative sequence prediction model based on many-to-many alignments, which is further augmented by the incorporation of joint n-gram features. Experimental results show improvement over achieved DirecTL in 2009. also explore a number diverse resource-free and language-independent approaches to transliteration mining, range from simple sophisticated.