Commit c10527cf by 曹润柘

合并分支 'caorunzhe' 到 'master'

Caorunzhe

查看合并请求 !247
parents 45504f6d 15a8552d
......@@ -382,7 +382,7 @@ y&=&\beta_0 y_{\pi_1} \beta_1 y_{\pi_2} ... \beta_{m-1} y_{\pi_m} \beta_m
\subsection{翻译特征}
\parinterval 在层次短语模型中,每个翻译推导都有一个模型得分$\textrm{score}(d,\seq{s},\seq{t})$$\textrm{score}(d,\seq{s},\seq{t})$是若干特征的线性加权之和:$\textrm{score}(d,\seq{t},\seq{s})=\sum_{i=1}^M\lambda_i\cdot h_i (d,\seq{t},\seq{s})$,其中$\lambda_i$是特征权重,$h_i (d,\seq{t},\seq{s})$是特征函数。层次短语模型的特征包括与规则相关的特征和语言模型特征,如下:
\parinterval 在层次短语模型中,每个翻译推导都有一个模型得分$\textrm{score}(d,\seq{t},\seq{s})$$\textrm{score}(d,\seq{t},\seq{s})$是若干特征的线性加权之和:$\textrm{score}(d,\seq{t},\seq{s})=\sum_{i=1}^M\lambda_i\cdot h_i (d,\seq{t},\seq{s})$,其中$\lambda_i$是特征权重,$h_i (d,\seq{t},\seq{s})$是特征函数。层次短语模型的特征包括与规则相关的特征和语言模型特征,如下:
\parinterval 对于每一条翻译规则LHS$\to \langle \alpha, \beta ,\sim \rangle$,有:
......@@ -438,7 +438,7 @@ h_i (d,\seq{t},\seq{s})=\sum_{r \in d}h_i (r)
\parinterval 层次短语模型解码的目标是找到模型得分最高的推导,即:
\begin{eqnarray}
\hat{d} = \argmax_{d}\ \textrm{score}(d,\seq{s},\seq{t})
\hat{d} = \argmax_{d}\ \textrm{score}(d,\seq{t},\seq{s})
\label{eq:8-7}
\end{eqnarray}
......
......@@ -2312,13 +2312,12 @@ year = {2012}
}
@article{shannon1949communication,
title ={Communication theory of secrecy systems},
author ={Shannon, Claude E},
author ={Claude E. Shannon},
journal ={Bell system technical journal},
volume ={28},
number ={4},
pages ={656--715},
year ={1949},
publisher ={Wiley Online Library}
year ={1949}
}
@inproceedings{DBLP:conf/acl/Moore04,
author = {Robert C. Moore},
......@@ -2352,8 +2351,8 @@ year = {2012}
}
@article{1998Grammar,
title={Grammar Inference and Statistical Machine Translation},
author={Ye-Yi Wang and Jaime Carbonell},
year={1998},
author={Ye-Yi Wang and Wayne Ward},
year={1999},
publisher={Carnegie Mellon University}
}
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论