作者: Jinxi Xu , John Broglio , Bruce Croft
DOI:
关键词: Part-of-speech tagging 、 Context (language use) 、 Computer science 、 Speech recognition 、 Bigram 、 Part of speech 、 Task (project management) 、 Performance comparison 、 Natural language processing 、 Artificial intelligence 、 Volume (computing)
摘要: Part of speech tagging is a task to assign part speeches words depending on the context. This paper describes bigram model for English and some implementation issues in developing tagger, Jtag, which designed effectively efficiently tag large volume free texts. Timing performance comparison with another similar system show that Jtag both effective efficient, thus especially suitable applications such information retrieval.