MIT自然语言处理第四讲:标注(第三部分)
自然语言处理:标注
Natural Language Processing: Tagging
作者:Regina Barzilay(MIT,EECS Department, November 15, 2004)
译者:我爱自然语言处理(www.52nlp.cn ,2009年3月24日)
三、 马尔科夫模型(Markov Model)
a) 直观(Intuition):对于序列中的每个单词挑选最可能的标记(Pick the most likely tag for each word of a sequence)
i. 我们将对P(T,S)建模,其中T是一个标记序列,S是一个单词序列(We will model P(T,S), where T is a sequence of tags, and S is a sequence of words)
ii. P({T}delim{|}{S}{})={P(T,S)}/{sum{T}{}{P(T,S)}}
Tagger(S)= argmax_{T in T^n}logP({T}delim{|}{S}{})
= argmax_{T in T^n}logP({T,S}{})
b) 参数估计(Parameter Estimation)
i. 应用链式法则(Apply chain rule):
P(T,S)={prod{j=1}{n}{P({T_j}delim{|}{S_1,…S_{j-1},T_1,…,T_{j-1}}{})}}*
P({S_j}delim{|}{S_1,…S_{j-1}T_1,…,T_{j}}{})
ii. 独立性假设(马尔科夫假设)(Assume independence (Markov assumption)):
={prod{j=1}{n}{P({T_j}delim{|}{T_{j-2},T_{j-1}}{})}}*P({S_j}delim{|}{T_j}{})
c) 举例(Example)
i. They/PRP never/RB stop/VB thinking/VBG about/IN new/JJ ways/NNS to/TO harm/VB our/PROPcountry/NNand/CCour/PRP people/NN, and/CC neither/DT do/VB we/PRP.
ii. P(T, S)=P(PRP|S, S)∗P(They|PRP)∗P(RB|S, PRP)∗P(never|RB)∗…
d) 估计转移概率(Estimating Transition Probabilities)
P({T_j}delim{|}{T_{j-2},T_{j-1}}{})=
{lambda_1}*{{Count(T_{j-2},T_{j-1},T_j)}/{Count(T_{j-2},T_{j-1})}}
+{lambda_2}*{{Count(T_{j-1},T_j)}/{Count(T_{j-1})}}
+{lambda_3}*{{Count(T_j)}/{Count(sum{i}{}{T_i})}}
e) 估计发射概率(Estimating Emission Probabilities)
P({S_j}delim{|}{T_j}{})={Count(S_j,T_j)}/{Count(T_j)}
i. 问题(Problem): 未登录词或罕见词(unknown or rare words)
1. 专有名词(Proper names)
“King Abdullah of Jordan, the King of Morocco, I mean, there’s a series of places — Qatar, Oman – I mean, places that are developing— Bahrain — they’re all developing the habits of free societies.”
2. 新词(New words)
“They misunderestimated me.”
f) 处理低频词(Dealing with Low Frequency Words)
i. 将词表分为两个集合(Split vocabulary into two sets)
1. 常用词(Frequent words)— 在训练集中出现超过5次的词(words occurring more than 5 times in training)
2. 低频词(Low frequency words)— 训练集中的其他词(all other words)
ii. 依据前缀、后缀等将低频词映射到一个小的、有限的集合中(Map low frequency words into a small, finite set, depending on prefixes, suffixes etc. (see Bikel et al., 1998))
附:课程及课件pdf下载MIT英文网页地址:
http://people.csail.mit.edu/regina/6881/