03.07.2013 Views

NP - 北京大学中国语言学研究中心

NP - 北京大学中国语言学研究中心

NP - 北京大学中国语言学研究中心

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

基于HMM的<strong>NP</strong>组块边界标注<br />

(1)带有词性标记、组块边界标记的语料库Corpus<br />

(2)可观察符号序列:词性标记对序列<br />

(3)隐状态:5个可能的<strong>NP</strong>组块边界标记(chunk_tag)<br />

(4)通过对Corpus的统计,得到:<br />

(I)状态转移矩阵;<br />

(II)每个状态输出不同词性标记对的概率;<br />

$ The prosecutor said in closing that …<br />

<br />

[ I<br />

<br />

]<br />

<br />

O<br />

<br />

[<br />

<br />

]<br />

29

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!