70 lines
1.8 KiB
Plaintext
70 lines
1.8 KiB
Plaintext
.. Copyright (C) 2001-2023 NLTK Project
|
|
.. For license information, see LICENSE.TXT
|
|
|
|
===============
|
|
Grammar Parsing
|
|
===============
|
|
|
|
Grammars can be parsed from strings:
|
|
|
|
>>> from nltk import CFG
|
|
>>> grammar = CFG.fromstring("""
|
|
... S -> NP VP
|
|
... PP -> P NP
|
|
... NP -> Det N | NP PP
|
|
... VP -> V NP | VP PP
|
|
... Det -> 'a' | 'the'
|
|
... N -> 'dog' | 'cat'
|
|
... V -> 'chased' | 'sat'
|
|
... P -> 'on' | 'in'
|
|
... """)
|
|
>>> grammar
|
|
<Grammar with 14 productions>
|
|
>>> grammar.start()
|
|
S
|
|
>>> grammar.productions()
|
|
[S -> NP VP, PP -> P NP, NP -> Det N, NP -> NP PP, VP -> V NP, VP -> VP PP,
|
|
Det -> 'a', Det -> 'the', N -> 'dog', N -> 'cat', V -> 'chased', V -> 'sat',
|
|
P -> 'on', P -> 'in']
|
|
|
|
Probabilistic CFGs:
|
|
|
|
>>> from nltk import PCFG
|
|
>>> toy_pcfg1 = PCFG.fromstring("""
|
|
... S -> NP VP [1.0]
|
|
... NP -> Det N [0.5] | NP PP [0.25] | 'John' [0.1] | 'I' [0.15]
|
|
... Det -> 'the' [0.8] | 'my' [0.2]
|
|
... N -> 'man' [0.5] | 'telescope' [0.5]
|
|
... VP -> VP PP [0.1] | V NP [0.7] | V [0.2]
|
|
... V -> 'ate' [0.35] | 'saw' [0.65]
|
|
... PP -> P NP [1.0]
|
|
... P -> 'with' [0.61] | 'under' [0.39]
|
|
... """)
|
|
|
|
Chomsky Normal Form grammar (Test for bug 474)
|
|
|
|
>>> g = CFG.fromstring("VP^<TOP> -> VBP NP^<VP-TOP>")
|
|
>>> g.productions()[0].lhs()
|
|
VP^<TOP>
|
|
|
|
Grammars can contain both empty strings and empty productions:
|
|
|
|
>>> from nltk.grammar import CFG
|
|
>>> from nltk.parse.generate import generate
|
|
>>> grammar = CFG.fromstring("""
|
|
... S -> A B
|
|
... A -> 'a'
|
|
... # An empty string:
|
|
... B -> 'b' | ''
|
|
... """)
|
|
>>> list(generate(grammar))
|
|
[['a', 'b'], ['a', '']]
|
|
>>> grammar = CFG.fromstring("""
|
|
... S -> A B
|
|
... A -> 'a'
|
|
... # An empty production:
|
|
... B -> 'b' |
|
|
... """)
|
|
>>> list(generate(grammar))
|
|
[['a', 'b'], ['a']]
|