update

Section02-Words-Trees-Probs/section02.test.tex

-% !Mode:: "TeX:GBK"
-
-\def\CTeXPreproc{Created by ctex v0.2.13, don't edit!}
-\documentclass[cjk,t,compress,12pt]{beamer}
-%\documentclass{article}
-%\usepackage{beamerarticle}
-\usepackage{pstricks}
-\usepackage{etex}
-\usepackage{eso-pic,graphicx}
-\usepackage{fancybox}
-\usepackage{amsmath,amssymb}
-\usepackage{setspace}
-\usepackage{xcolor}
-\usepackage{CJK}
-\usepackage{tikz}
-\usepackage{tikz-qtree}
-\usepackage{hyperref}
-\usepackage{array}
-
-\usepgflibrary{arrows} % LATEX and plain TEX and pure pgf
-\usetikzlibrary{arrows} % LATEX and plain TEX when using Tik Z
-\usetikzlibrary{decorations}
-\usetikzlibrary{arrows,shapes}
-
-\usetikzlibrary{shadows} % LATEX and plain TEX when using Tik Z
-
-\usetikzlibrary{positioning,fit,calc}
-
-\usetikzlibrary{mindmap,backgrounds} % mind map
-
-\DeclareMathOperator*{\argmax}{arg\,max}
-\DeclareMathOperator*{\argmin}{arg\,min}
-
-\setbeamertemplate{items}[ball]
-\usefonttheme[onlymath]{serif}  % fout of math
-
-\definecolor{ugreen}{rgb}{0,0.5,0}
-\definecolor{lgreen}{rgb}{0.9,1,0.8}
-\definecolor{xtgreen1}{rgb}{0.824,0.898,0.8}
-\definecolor{xtgreen}{rgb}{0.914,0.945,0.902}
-\definecolor{lightgray}{gray}{0.85}
-
-\setbeamercolor{uppercol}{fg=white,bg=ugreen}
-\setbeamercolor{lowercol}{fg=black,bg=xtgreen}
-
-%\definecolor{ublue}{rgb}{0,0.298,0.525}
-\definecolor{ublue}{rgb}{0.152,0.250,0.545}
-\setbeamercolor{uppercolblue}{fg=white,bg=ublue}
-\setbeamercolor{lowercolblue}{fg=black,bg=blue!10}
-
-
-%\usetheme{default}
-%\usetheme{Darmstadt}
-%\usetheme{Madrid}
-%\usetheme{Frankfurt}
-%\usetheme{Dresden}
-%\usetheme{Boadilla}
-%\usecolortheme{dolphin}
-
-
-\usefonttheme[onlylarge]{structurebold}
-
-\begin{CJK}{GBK}{song}
-\end{CJK}
-
-\setbeamerfont*{frametitle}{size=\large,series=\bfseries}
-\setbeamertemplate{navigation symbols}{\begin{CJK}{GBK}{hei} 第二章 词法、语法及概率思想基础 \hspace*{2em} 肖桐\&朱靖波 \end{CJK} \hspace*{2em} \today \hspace*{2em} \insertframenumber{}/\inserttotalframenumber}
-
-\setbeamertemplate{itemize items}[circle] % if you want a circle
-\setbeamertemplate{itemize subitem}[triangle] % if you wnat a triangle
-\setbeamertemplate{itemize subsubitem}[ball] % if you want a ball
-
-\begin{document}
-
-\begin{CJK}{GBK}{you}
-
-\title{\Large{词法、语法及概率思想基础}}
-\author{\large{\textbf{肖桐\ \ 朱靖波}}}
-\institute{
-\blue{\url{xiaotong@mail.neu.edu.cn}} \black{} \\
-\blue{\url{zhujingbo@mail.neu.edu.cn}} \black{} \\
-\vspace{1.0em}
-东北大学 自然语言处理实验室 \\
-\blue{\underline{\url{http://www.nlplab.com}}} \black{} \\
-\vspace{0.2cm}
-\hspace{0.1cm} \includegraphics[scale=0.1]{../Figures/logo.pdf}
-}
-\date{}
-
-\maketitle
-
-\setlength{\leftmargini}{1em}
-\setlength{\leftmarginii}{1em}
-
-
-\section{中文分词}
-
-%%% 进一步扩展，基于n-gram LM的方法
-\begin{frame}{进一步扩展：基于$n$-gram语言模型的方法}
-
-\begin{itemize}
-\item 这种方法也被称作基于1-gram(统计)语言模型的方法\\
-      所谓统计语言模型就是计算$\textrm{P}(w_1 w_2 ... w_m)$的概率
-\end{itemize}
-
-{\scriptsize
-\tabcolsep 5pt
-\begin{tabular}{l | l | l l l}
-链式法则 & 1-gram & 2-gram & ... & $n$-gram \\
-$\textrm{P}(w_1 w_2 ... w_n)=$ & $\textrm{P}(w_1 w_2 ... w_n)=$ & $\textrm{P}(w_1 w_2 ... w_n)=$ & ... & $\textrm{P}(w_1 w_2 ... w_n)=$ \\
-$\textrm{P}(w_1) \times$ & $\textrm{P}(w_1) \times$ & $\textrm{P}(w_1) \times$ & ... & $\textrm{P}(w_1) \times$ \\
-$\textrm{P}(w_2|w_1) \times$ & $\textrm{P}(w_2) \times$ & $\textrm{P}(w_2|w_1) \times$ & ... & $\textrm{P}(w_2|w_1) \times$ \\
-$\textrm{P}(w_3|w_1 w_2) \times$ & $\textrm{P}(w_3) \times$ & $\textrm{P}(w_3|w_2) \times$ & ... & $\textrm{P}(w_3|w_1 w_2) \times$ \\
-$\textrm{P}(w_4|w_1 w_2 w_3) \times$ & $\textrm{P}(w_4) \times$ & $\textrm{P}(w_4|w_3) \times$ & ... & $\textrm{P}(w_4|w_1 w_2 w_3) \times$ \\
-... & ... & ... & ... & ... \\
-$\textrm{P}(w_m|w_1...w_{m-1})$ & $\textrm{P}(w_m)$ & $\textrm{P}(w_m|w_{m-1})$ & ... & $\textrm{P}(w_m|w_{m-n+1} ... w_{m-1})$ \\
-\end{tabular}
-}
-
-\begin{itemize}
-\item<2-> \textbf{$n$-gram语言模型}的核心思想就是当前词($w_m$)出现的概率只依赖于前$n-1$个词($w_{m-n+1} ... w_{m-1}$)
-
-\vspace{-2em}
-
-\begin{eqnarray}
-&   & \textrm{P}_{2\textrm{-gram}}(\textrm{'确实/现在/数据/很/多'}) \nonumber \\
-& = & \textrm{P}(\textrm{'确实'}) \times \textrm{P}(\textrm{'现在'$|$'确实'}) \times \textrm{P}(\textrm{'数据'$|$'现在'}) \times  \nonumber \\
-&   & \textrm{P}(\textrm{'很'$|$'数据'}) \times \textrm{P}(\textrm{'多'$|$'很'}) \nonumber
-\end{eqnarray}
-
-\vspace{-1em}
-
-\item<2-> \textbf{训练} - 相对频率估计：$\textrm{P}(\textrm{'现在'$|$'确实'}) = \frac{count(\textrm{'确实 现在'})}{count(\textrm{'确实'})}$
-
-\end{itemize}
-
-\end{frame}
-
-\subsection{统计思想}
-
-\subsection{统计建模实例1：基于全切分的概率分词}
-
-\end{CJK}
-\end{document}