第09章 建立基于特征的文法
import nltk
- 怎样用特征扩展上下文无关文法框架，以获得更细粒度的对文法类别和产生式的控制？
- 特征结构的主要形式化属性是什么，如何使用它们来计算？
- 用基于特征的文法能捕捉到什么语言模式和文法结构？
9.1 文法特征
基于规则的文法上下文中，特征和特征值对被称为特征结构
kim = {'CAT': 'NP', 'ORTH': 'Kim', 'REF': 'k'}
chase = {'CAT': 'V', 'ORTH': 'chased', 'REL': 'chase'}
chase['AGT'] = 'sbj'
chase['PAT'] = 'obj'
一个简单的假设：在动词直接左侧和右侧的NP 分别是主语和宾语。
sent = "Kim chased Lee"
tokens = sent.split()
lee = {'CAT': 'NP', 'ORTH': 'Lee', 'REF': 'l'}
def lex2fs(word):
for fs in [kim, lee, chase]:
if fs['ORTH'] == word:
return fs
subj, verb, obj = lex2fs(tokens[0]), lex2fs(tokens[1]), lex2fs(tokens[2])
verb['AGT'] = subj['REF'] # agent of 'chase' is Kim
verb['PAT'] = obj['REF'] # patient of 'chase' is Lee
for k in ['ORTH', 'REL', 'AGT', 'PAT']: # check featstruct of 'chase'
print("%-5s => %s" % (k, verb[k]))
ORTH => chased
REL => chase
AGT => k
PAT => l
surprise = {'CAT': 'V', 'ORTH': 'surprised', 'REL': 'surprise',
'SRC': 'sbj', 'EXP': 'obj'}
句法协议
动词的形态属性与主语名词短语的句法属性一起变化。这种一起变化被称为协议（agreement）。
表9-1. 英语规则动词的协议范式
使用属性和约束
例9-1. 基于特征的文法的例子。
nltk.data.show_cfg('grammars/book_grammars/feat0.fcfg')
% start S
# ###################
# Grammar Productions
# ###################
# S expansion productions
S -> NP[NUM=?n] VP[NUM=?n]
# NP expansion productions
NP[NUM=?n] -> N[NUM=?n]
NP[NUM=?n] -> PropN[NUM=?n]
NP[NUM=?n] -> Det[NUM=?n] N[NUM=?n]
NP[NUM=pl] -> N[NUM=pl]
# VP expansion productions
VP[TENSE=?t, NUM=?n] -> IV[TENSE=?t, NUM=?n]
VP[TENSE=?t, NUM=?n] -> TV[TENSE=?t, NUM=?n] NP
# ###################
# Lexical Productions
# ###################
Det[NUM=sg] -> 'this' | 'every'
Det[NUM=pl] -> 'these' | 'all'
Det -> 'the' | 'some' | 'several'
PropN[NUM=sg]-> 'Kim' | 'Jody'
N[NUM=sg] -> 'dog' | 'girl' | 'car' | 'child'
N[NUM=pl] -> 'dogs' | 'girls' | 'cars' | 'children'
IV[TENSE=pres, NUM=sg] -> 'disappears' | 'walks'
TV[TENSE=pres, NUM=sg] -> 'sees' | 'likes'
IV[TENSE=pres, NUM=pl] -> 'disappear' | 'walk'
TV[TENSE=pres, NUM=pl] -> 'see' | 'like'
IV[TENSE=past] -> 'disappeared' | 'walked'
TV[TENSE=past] -> 'saw' | 'liked'
例9-2. 跟踪基于特征的图表分析器
tokens = 'Kim likes children'.split()
from nltk import load_parser
cp = load_parser('grammars/book_grammars/feat0.fcfg', trace=2)
for tree in cp.parse(tokens):
print(tree)
|.Kim .like.chil.|
Leaf Init Rule:
|[----] . .| [0:1] 'Kim'
|. [----] .| [1:2] 'likes'
|. . [----]| [2:3] 'children'
Feature Bottom Up Predict Combine Rule:
|[----] . .| [0:1] PropN[NUM='sg'] -> 'Kim' *
Feature Bottom Up Predict Combine Rule:
|[----] . .| [0:1] NP[NUM='sg'] -> PropN[NUM='sg'] *
Feature Bottom Up Predict Combine Rule:
|[----> . .| [0:1] S[] -> NP[NUM=?n] * VP[NUM=?n] {?n: 'sg'}
Feature Bottom Up Predict Combine Rule:
|. [----] .| [1:2] TV[NUM='sg', TENSE='pres'] -> 'likes' *
Feature Bottom Up Predict Combine Rule:
|. [----> .| [1:2] VP[NUM=?n, TENSE=?t] -> TV[NUM=?n, TENSE=?t] * NP[] {?n: 'sg', ?t: 'pres'}
Feature Bottom Up Predict Combine Rule:
|. . [----]| [2:3] N[NUM='pl'] -> 'children' *
Feature Bottom Up Predict Combine Rule:
|. . [----]| [2:3] NP[NUM='pl'] -> N[NUM='pl'] *
Feature Bottom Up Predict Combine Rule:
|. . [---->| [2:3] S[] -> NP[NUM=?n] * VP[NUM=?n] {?n: 'pl'}
Feature Single Edge Fundamental Rule:
|. [---------]| [1:3] VP[NUM='sg', TENSE='pres'] -> TV[NUM='sg', TENSE='pres'] NP[] *
Feature Single Edge Fundamental Rule:
|[==============]| [0:3] S[] -> NP[NUM='sg'] VP[NUM='sg'] *
(S[]
(NP[NUM='sg'] (PropN[NUM='sg'] Kim))
(VP[NUM='sg', TENSE='pres']
(TV[NUM='sg', TENSE='pres'] likes)
(NP[NUM='pl'] (N[NUM='pl'] children))))
术语
9.2 处理特征结构
NLTK 中的特征结构使用构造函数FeatStruct()声明。原子特征值可以是字符串或整数。
fs1 = nltk.FeatStruct(TENSE='past', NUM='sg')
print(fs1)
[ NUM = 'sg' ]
[ TENSE = 'past' ]
fs1 = nltk.FeatStruct(PER=3, NUM='pl', GND='fem')
print(fs1['GND'])
fem
fs1['CASE'] = 'acc'
fs2 = nltk.FeatStruct(POS='N', AGR=fs1)
print(fs2)
[ [ CASE = 'acc' ] ]
[ AGR = [ GND = 'fem' ] ]
[ [ NUM = 'pl' ] ]
[ [ PER = 3 ] ]
[ ]
[ POS = 'N' ]
print(fs2['AGR'])
[ CASE = 'acc' ]
[ GND = 'fem' ]
[ NUM = 'pl' ]
[ PER = 3 ]
print(fs2['AGR']['PER'])
3
print(nltk.FeatStruct("[POS='N', AGR=[PER=3, NUM='pl', GND='fem']]"))
[ [ GND = 'fem' ] ]
[ AGR = [ NUM = 'pl' ] ]
[ [ PER = 3 ] ]
[ ]
[ POS = 'N' ]
print(nltk.FeatStruct(NAME='Lee', TELNO='01 27 86 42 96', AGE=33))
[ AGE = 33 ]
[ NAME = 'Lee' ]
[ TELNO = '01 27 86 42 96' ]
print(nltk.FeatStruct("""[NAME='Lee', ADDRESS=(1)[NUMBER=74, STREET='rue Pascal'],SPOUSE=[NAME='Kim', ADDRESS->(1)]]"""))
[ ADDRESS = (1) [ NUMBER = 74 ] ]
[ [ STREET = 'rue Pascal' ] ]
[ ]
[ NAME = 'Lee' ]
[ ]
[ SPOUSE = [ ADDRESS -> (1) ] ]
[ [ NAME = 'Kim' ] ]
print(nltk.FeatStruct("[A='a', B=(1)[C='c'], D->(1), E->(1)]"))
[ A = 'a' ]
[ ]
[ B = (1) [ C = 'c' ] ]
[ ]
[ D -> (1) ]
[ E -> (1) ]
包含和统一
fs1 = nltk.FeatStruct(NUMBER=74, STREET='rue Pascal')
fs2 = nltk.FeatStruct(CITY='Paris')
print(fs2.unify(fs1))
[ CITY = 'Paris' ]
[ NUMBER = 74 ]
[ STREET = 'rue Pascal' ]
fs0 = nltk.FeatStruct(A='a')
fs1 = nltk.FeatStruct(A='b')
fs2 = fs0.unify(fs1)
print(fs2)
None
fs0 = nltk.FeatStruct("""[NAME=Lee,
ADDRESS=[NUMBER=74,
STREET='rue Pascal'],
SPOUSE= [NAME=Kim,
ADDRESS=[NUMBER=74,
STREET='rue Pascal']]]""")
print(fs0)
[ ADDRESS = [ NUMBER = 74 ] ]
[ [ STREET = 'rue Pascal' ] ]
[ ]
[ NAME = 'Lee' ]
[ ]
[ [ ADDRESS = [ NUMBER = 74 ] ] ]
[ SPOUSE = [ [ STREET = 'rue Pascal' ] ] ]
[ [ ] ]
[ [ NAME = 'Kim' ] ]
fs1 = nltk.FeatStruct("[SPOUSE = [ADDRESS = [CITY = Paris]]]")
print(fs1.unify(fs0))
[ ADDRESS = [ NUMBER = 74 ] ]
[ [ STREET = 'rue Pascal' ] ]
[ ]
[ NAME = 'Lee' ]
[ ]
[ [ [ CITY = 'Paris' ] ] ]
[ [ ADDRESS = [ NUMBER = 74 ] ] ]
[ SPOUSE = [ [ STREET = 'rue Pascal' ] ] ]
[ [ ] ]
[ [ NAME = 'Kim' ] ]
fs2 = nltk.FeatStruct("""[NAME=Lee, ADDRESS=(1)[NUMBER=74, STREET='rue Pascal'],
SPOUSE=[NAME=Kim, ADDRESS->(1)]]""")
print(fs1.unify(fs2))
[ [ CITY = 'Paris' ] ]
[ ADDRESS = (1) [ NUMBER = 74 ] ]
[ [ STREET = 'rue Pascal' ] ]
[ ]
[ NAME = 'Lee' ]
[ ]
[ SPOUSE = [ ADDRESS -> (1) ] ]
[ [ NAME = 'Kim' ] ]
fs1 = nltk.FeatStruct("[ADDRESS1=[NUMBER=74, STREET='rue Pascal']]")
fs2 = nltk.FeatStruct("[ADDRESS1=?x, ADDRESS2=?x]")
print(fs2)
[ ADDRESS1 = ?x ]
[ ADDRESS2 = ?x ]
print(fs2.unify(fs1))
[ ADDRESS1 = (1) [ NUMBER = 74 ] ]
[ [ STREET = 'rue Pascal' ] ]
[ ]
[ ADDRESS2 -> (1) ]
9.3 扩展基于特征的文法
子类别
核心词回顾
助动词与倒装
无限制依赖成分
例9-3. 具有倒装从句和长距离依赖的产生式的文法，使用斜线类别。
nltk.data.show_cfg('grammars/book_grammars/feat1.fcfg')
% start S
# ###################
# Grammar Productions
# ###################
S[-INV] -> NP VP
S[-INV]/?x -> NP VP/?x
S[-INV] -> NP S/NP
S[-INV] -> Adv[+NEG] S[+INV]
S[+INV] -> V[+AUX] NP VP
S[+INV]/?x -> V[+AUX] NP VP/?x
SBar -> Comp S[-INV]
SBar/?x -> Comp S[-INV]/?x
VP -> V[SUBCAT=intrans, -AUX]
VP -> V[SUBCAT=trans, -AUX] NP
VP/?x -> V[SUBCAT=trans, -AUX] NP/?x
VP -> V[SUBCAT=clause, -AUX] SBar
VP/?x -> V[SUBCAT=clause, -AUX] SBar/?x
VP -> V[+AUX] VP
VP/?x -> V[+AUX] VP/?x
# ###################
# Lexical Productions
# ###################
V[SUBCAT=intrans, -AUX] -> 'walk' | 'sing'
V[SUBCAT=trans, -AUX] -> 'see' | 'like'
V[SUBCAT=clause, -AUX] -> 'say' | 'claim'
V[+AUX] -> 'do' | 'can'
NP[-WH] -> 'you' | 'cats'
NP[+WH] -> 'who'
Adv[+NEG] -> 'rarely' | 'never'
NP/NP ->
Comp -> 'that'
tokens = 'who do you claim that you like'.split()
from nltk import load_parser
cp = load_parser('grammars/book_grammars/feat1.fcfg')
for tree in cp.parse(tokens):
print(tree)
(S[-INV]
(NP[+WH] who)
(S[+INV]/NP[]
(V[+AUX] do)
(NP[-WH] you)
(VP[]/NP[]
(V[-AUX, SUBCAT='clause'] claim)
(SBar[]/NP[]
(Comp[] that)
(S[-INV]/NP[]
(NP[-WH] you)
(VP[]/NP[] (V[-AUX, SUBCAT='trans'] like) (NP[]/NP[] )))))))
tokens = 'you claim that you like cats'.split()
for tree in cp.parse(tokens):
print(tree)
(S[-INV]
(NP[-WH] you)
(VP[]
(V[-AUX, SUBCAT='clause'] claim)
(SBar[]
(Comp[] that)
(S[-INV]
(NP[-WH] you)
(VP[] (V[-AUX, SUBCAT='trans'] like) (NP[-WH] cats))))))
tokens = 'rarely do you sing'.split()
for tree in cp.parse(tokens):
print(tree)
(S[-INV]
(Adv[+NEG] rarely)
(S[+INV]
(V[+AUX] do)
(NP[-WH] you)
(VP[] (V[-AUX, SUBCAT='intrans'] sing))))
9.4 小结
- 上下文无关文法的传统分类是原子符号。特征结构的一个重要的作用是捕捉精细的区分，否则将需要数量翻倍的原子类别。
- 通过使用特征值上的变量，我们可以表达文法产生式中的限制，允许不同的特征规格的实现可以相互依赖。
- 通常情况下，我们在词汇层面指定固定的特征值，限制短语中的特征值与它们的原子中的对应值统一。
- 特征值可以是原子的或复杂的。原子值的一个特定类别是布尔值，按照惯例用[+/- feat]表示。
- 两个特征可以共享一个值（原子的或复杂的）。具有共享值的结构被称为重入。共享的值被表示为AVM 中的数字索引（或标记）。
- 一个特征结构中的路径是一个特征的元组，对应从图的根开始的弧的序列上的标签。
- 两条路径是等价的，如果它们共享一个值。
- 包含的特征结构是偏序的。FS0 包含FS1，当FS0 比FS1 更一般（较少信息）。
- 两种结构FS0 和FS1 的统一，如果成功，就是包含FS0 和FS1 的合并信息的特征结构FS2。
- 如果统一在FS 中指定一条路径π，那么它也指定等效与π的每个路径π’。
- 我们可以使用特征结构建立对大量广泛语言学现象的简洁的分析，包括动词子类别，倒装结构，无限制依赖结构和格支配。
致谢
《Python自然语言处理》 ，作者：Steven Bird, Ewan Klein & Edward Loper，是实践性很强的一部入门读物，2009年第一版，2015年第二版，本学习笔记结合上述版本，对部分内容进行了延伸学习、练习，在此分享，期待对大家有所帮助，欢迎加我微信（验证：NLP），一起学习讨论，不足之处，欢迎指正。
参考文献