Segmental HMM-based Part-of-speech Tagger
This paper presents a solution in order to solve the problem of using HMM-based POS tagger in some languages where a word can be comprised of several tokens. Viterbi algorithm is modified in order to support segment of words within a model state. In the other word, the proposed system has a built-in tokenizer where indicates words boundaries as well as its corresponding tag sequence.
Mohammad Hadi Bokaei Hossein Sameti Mohammad Bahrani Bagher Babaali
Speech Processing Lab Sharif University of Technology Tehran, Iran
国际会议
上海
英文
52-56
2010-10-20（万方平台首次上网日期，不代表论文的发表时间）