373 lines
11 KiB
Plaintext
373 lines
11 KiB
Plaintext
|
.. Copyright (C) 2001-2023 NLTK Project
|
||
|
|
.. For license information, see LICENSE.TXT
|
||
|
|
|
||
|
|
==========
|
||
|
|
Chunking
|
||
|
|
==========
|
||
|
|
|
||
|
|
>>> from nltk.chunk import *
|
||
|
|
>>> from nltk.chunk.util import *
|
||
|
|
>>> from nltk.chunk.regexp import *
|
||
|
|
>>> from nltk import Tree
|
||
|
|
|
||
|
|
>>> tagged_text = "[ The/DT cat/NN ] sat/VBD on/IN [ the/DT mat/NN ] [ the/DT dog/NN ] chewed/VBD ./."
|
||
|
|
>>> gold_chunked_text = tagstr2tree(tagged_text)
|
||
|
|
>>> unchunked_text = gold_chunked_text.flatten()
|
||
|
|
|
||
|
|
Chunking uses a special regexp syntax for rules that delimit the chunks. These
|
||
|
|
rules must be converted to 'regular' regular expressions before a sentence can
|
||
|
|
be chunked.
|
||
|
|
|
||
|
|
>>> tag_pattern = "<DT>?<JJ>*<NN.*>"
|
||
|
|
>>> regexp_pattern = tag_pattern2re_pattern(tag_pattern)
|
||
|
|
>>> regexp_pattern
|
||
|
|
'(<(DT)>)?(<(JJ)>)*(<(NN[^\\{\\}<>]*)>)'
|
||
|
|
|
||
|
|
Construct some new chunking rules.
|
||
|
|
|
||
|
|
>>> chunk_rule = ChunkRule(r"<.*>+", "Chunk everything")
|
||
|
|
>>> strip_rule = StripRule(r"<VBD|IN|\.>", "Strip on verbs/prepositions")
|
||
|
|
>>> split_rule = SplitRule("<DT><NN>", "<DT><NN>",
|
||
|
|
... "Split successive determiner/noun pairs")
|
||
|
|
|
||
|
|
|
||
|
|
Create and score a series of chunk parsers, successively more complex.
|
||
|
|
|
||
|
|
>>> chunk_parser = RegexpChunkParser([chunk_rule], chunk_label='NP')
|
||
|
|
>>> chunked_text = chunk_parser.parse(unchunked_text)
|
||
|
|
>>> print(chunked_text)
|
||
|
|
(S
|
||
|
|
(NP
|
||
|
|
The/DT
|
||
|
|
cat/NN
|
||
|
|
sat/VBD
|
||
|
|
on/IN
|
||
|
|
the/DT
|
||
|
|
mat/NN
|
||
|
|
the/DT
|
||
|
|
dog/NN
|
||
|
|
chewed/VBD
|
||
|
|
./.))
|
||
|
|
|
||
|
|
>>> chunkscore = ChunkScore()
|
||
|
|
>>> chunkscore.score(gold_chunked_text, chunked_text)
|
||
|
|
>>> print(chunkscore.precision())
|
||
|
|
0.0
|
||
|
|
|
||
|
|
>>> print(chunkscore.recall())
|
||
|
|
0.0
|
||
|
|
|
||
|
|
>>> print(chunkscore.f_measure())
|
||
|
|
0
|
||
|
|
|
||
|
|
>>> for chunk in sorted(chunkscore.missed()): print(chunk)
|
||
|
|
(NP The/DT cat/NN)
|
||
|
|
(NP the/DT dog/NN)
|
||
|
|
(NP the/DT mat/NN)
|
||
|
|
|
||
|
|
>>> for chunk in chunkscore.incorrect(): print(chunk)
|
||
|
|
(NP
|
||
|
|
The/DT
|
||
|
|
cat/NN
|
||
|
|
sat/VBD
|
||
|
|
on/IN
|
||
|
|
the/DT
|
||
|
|
mat/NN
|
||
|
|
the/DT
|
||
|
|
dog/NN
|
||
|
|
chewed/VBD
|
||
|
|
./.)
|
||
|
|
|
||
|
|
>>> chunk_parser = RegexpChunkParser([chunk_rule, strip_rule],
|
||
|
|
... chunk_label='NP')
|
||
|
|
>>> chunked_text = chunk_parser.parse(unchunked_text)
|
||
|
|
>>> print(chunked_text)
|
||
|
|
(S
|
||
|
|
(NP The/DT cat/NN)
|
||
|
|
sat/VBD
|
||
|
|
on/IN
|
||
|
|
(NP the/DT mat/NN the/DT dog/NN)
|
||
|
|
chewed/VBD
|
||
|
|
./.)
|
||
|
|
>>> assert chunked_text == chunk_parser.parse(list(unchunked_text))
|
||
|
|
|
||
|
|
>>> chunkscore = ChunkScore()
|
||
|
|
>>> chunkscore.score(gold_chunked_text, chunked_text)
|
||
|
|
>>> chunkscore.precision()
|
||
|
|
0.5
|
||
|
|
|
||
|
|
>>> print(chunkscore.recall())
|
||
|
|
0.33333333...
|
||
|
|
|
||
|
|
>>> print(chunkscore.f_measure())
|
||
|
|
0.4
|
||
|
|
|
||
|
|
>>> for chunk in sorted(chunkscore.missed()): print(chunk)
|
||
|
|
(NP the/DT dog/NN)
|
||
|
|
(NP the/DT mat/NN)
|
||
|
|
|
||
|
|
>>> for chunk in chunkscore.incorrect(): print(chunk)
|
||
|
|
(NP the/DT mat/NN the/DT dog/NN)
|
||
|
|
|
||
|
|
>>> chunk_parser = RegexpChunkParser([chunk_rule, strip_rule, split_rule],
|
||
|
|
... chunk_label='NP')
|
||
|
|
>>> chunked_text = chunk_parser.parse(unchunked_text, trace=True)
|
||
|
|
# Input:
|
||
|
|
<DT> <NN> <VBD> <IN> <DT> <NN> <DT> <NN> <VBD> <.>
|
||
|
|
# Chunk everything:
|
||
|
|
{<DT> <NN> <VBD> <IN> <DT> <NN> <DT> <NN> <VBD> <.>}
|
||
|
|
# Strip on verbs/prepositions:
|
||
|
|
{<DT> <NN>} <VBD> <IN> {<DT> <NN> <DT> <NN>} <VBD> <.>
|
||
|
|
# Split successive determiner/noun pairs:
|
||
|
|
{<DT> <NN>} <VBD> <IN> {<DT> <NN>}{<DT> <NN>} <VBD> <.>
|
||
|
|
>>> print(chunked_text)
|
||
|
|
(S
|
||
|
|
(NP The/DT cat/NN)
|
||
|
|
sat/VBD
|
||
|
|
on/IN
|
||
|
|
(NP the/DT mat/NN)
|
||
|
|
(NP the/DT dog/NN)
|
||
|
|
chewed/VBD
|
||
|
|
./.)
|
||
|
|
|
||
|
|
>>> chunkscore = ChunkScore()
|
||
|
|
>>> chunkscore.score(gold_chunked_text, chunked_text)
|
||
|
|
>>> chunkscore.precision()
|
||
|
|
1.0
|
||
|
|
|
||
|
|
>>> chunkscore.recall()
|
||
|
|
1.0
|
||
|
|
|
||
|
|
>>> chunkscore.f_measure()
|
||
|
|
1.0
|
||
|
|
|
||
|
|
>>> chunkscore.missed()
|
||
|
|
[]
|
||
|
|
|
||
|
|
>>> chunkscore.incorrect()
|
||
|
|
[]
|
||
|
|
|
||
|
|
>>> chunk_parser.rules()
|
||
|
|
[<ChunkRule: '<.*>+'>, <StripRule: '<VBD|IN|\\.>'>,
|
||
|
|
<SplitRule: '<DT><NN>', '<DT><NN>'>]
|
||
|
|
|
||
|
|
Printing parsers:
|
||
|
|
|
||
|
|
>>> print(repr(chunk_parser))
|
||
|
|
<RegexpChunkParser with 3 rules>
|
||
|
|
>>> print(chunk_parser)
|
||
|
|
RegexpChunkParser with 3 rules:
|
||
|
|
Chunk everything
|
||
|
|
<ChunkRule: '<.*>+'>
|
||
|
|
Strip on verbs/prepositions
|
||
|
|
<StripRule: '<VBD|IN|\\.>'>
|
||
|
|
Split successive determiner/noun pairs
|
||
|
|
<SplitRule: '<DT><NN>', '<DT><NN>'>
|
||
|
|
|
||
|
|
Regression Tests
|
||
|
|
~~~~~~~~~~~~~~~~
|
||
|
|
ChunkParserI
|
||
|
|
------------
|
||
|
|
`ChunkParserI` is an abstract interface -- it is not meant to be
|
||
|
|
instantiated directly.
|
||
|
|
|
||
|
|
>>> ChunkParserI().parse([])
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
NotImplementedError
|
||
|
|
|
||
|
|
|
||
|
|
ChunkString
|
||
|
|
-----------
|
||
|
|
ChunkString can be built from a tree of tagged tuples, a tree of
|
||
|
|
trees, or a mixed list of both:
|
||
|
|
|
||
|
|
>>> t1 = Tree('S', [('w%d' % i, 't%d' % i) for i in range(10)])
|
||
|
|
>>> t2 = Tree('S', [Tree('t0', []), Tree('t1', ['c1'])])
|
||
|
|
>>> t3 = Tree('S', [('w0', 't0'), Tree('t1', ['c1'])])
|
||
|
|
>>> ChunkString(t1)
|
||
|
|
<ChunkString: '<t0><t1><t2><t3><t4><t5><t6><t7><t8><t9>'>
|
||
|
|
>>> ChunkString(t2)
|
||
|
|
<ChunkString: '<t0><t1>'>
|
||
|
|
>>> ChunkString(t3)
|
||
|
|
<ChunkString: '<t0><t1>'>
|
||
|
|
|
||
|
|
Other values generate an error:
|
||
|
|
|
||
|
|
>>> ChunkString(Tree('S', ['x']))
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: chunk structures must contain tagged tokens or trees
|
||
|
|
|
||
|
|
The `str()` for a chunk string adds spaces to it, which makes it line
|
||
|
|
up with `str()` output for other chunk strings over the same
|
||
|
|
underlying input.
|
||
|
|
|
||
|
|
>>> cs = ChunkString(t1)
|
||
|
|
>>> print(cs)
|
||
|
|
<t0> <t1> <t2> <t3> <t4> <t5> <t6> <t7> <t8> <t9>
|
||
|
|
>>> cs.xform('<t3>', '{<t3>}')
|
||
|
|
>>> print(cs)
|
||
|
|
<t0> <t1> <t2> {<t3>} <t4> <t5> <t6> <t7> <t8> <t9>
|
||
|
|
|
||
|
|
The `_verify()` method makes sure that our transforms don't corrupt
|
||
|
|
the chunk string. By setting debug_level=2, `_verify()` will be
|
||
|
|
called at the end of every call to `xform`.
|
||
|
|
|
||
|
|
>>> cs = ChunkString(t1, debug_level=3)
|
||
|
|
|
||
|
|
>>> # tag not marked with <...>:
|
||
|
|
>>> cs.xform('<t3>', 't3')
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Transformation generated invalid chunkstring:
|
||
|
|
<t0><t1><t2>t3<t4><t5><t6><t7><t8><t9>
|
||
|
|
|
||
|
|
>>> # brackets not balanced:
|
||
|
|
>>> cs.xform('<t3>', '{<t3>')
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Transformation generated invalid chunkstring:
|
||
|
|
<t0><t1><t2>{<t3><t4><t5><t6><t7><t8><t9>
|
||
|
|
|
||
|
|
>>> # nested brackets:
|
||
|
|
>>> cs.xform('<t3><t4><t5>', '{<t3>{<t4>}<t5>}')
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Transformation generated invalid chunkstring:
|
||
|
|
<t0><t1><t2>{<t3>{<t4>}<t5>}<t6><t7><t8><t9>
|
||
|
|
|
||
|
|
>>> # modified tags:
|
||
|
|
>>> cs.xform('<t3>', '<t9>')
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Transformation generated invalid chunkstring: tag changed
|
||
|
|
|
||
|
|
>>> # added tags:
|
||
|
|
>>> cs.xform('<t9>', '<t9><t10>')
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Transformation generated invalid chunkstring: tag changed
|
||
|
|
|
||
|
|
Chunking Rules
|
||
|
|
--------------
|
||
|
|
|
||
|
|
Test the different rule constructors & __repr__ methods:
|
||
|
|
|
||
|
|
>>> r1 = RegexpChunkRule('<a|b>'+ChunkString.IN_STRIP_PATTERN,
|
||
|
|
... '{<a|b>}', 'chunk <a> and <b>')
|
||
|
|
>>> r2 = RegexpChunkRule(re.compile('<a|b>'+ChunkString.IN_STRIP_PATTERN),
|
||
|
|
... '{<a|b>}', 'chunk <a> and <b>')
|
||
|
|
>>> r3 = ChunkRule('<a|b>', 'chunk <a> and <b>')
|
||
|
|
>>> r4 = StripRule('<a|b>', 'strip <a> and <b>')
|
||
|
|
>>> r5 = UnChunkRule('<a|b>', 'unchunk <a> and <b>')
|
||
|
|
>>> r6 = MergeRule('<a>', '<b>', 'merge <a> w/ <b>')
|
||
|
|
>>> r7 = SplitRule('<a>', '<b>', 'split <a> from <b>')
|
||
|
|
>>> r8 = ExpandLeftRule('<a>', '<b>', 'expand left <a> <b>')
|
||
|
|
>>> r9 = ExpandRightRule('<a>', '<b>', 'expand right <a> <b>')
|
||
|
|
>>> for rule in r1, r2, r3, r4, r5, r6, r7, r8, r9:
|
||
|
|
... print(rule)
|
||
|
|
<RegexpChunkRule: '<a|b>(?=[^\\}]*(\\{|$))'->'{<a|b>}'>
|
||
|
|
<RegexpChunkRule: '<a|b>(?=[^\\}]*(\\{|$))'->'{<a|b>}'>
|
||
|
|
<ChunkRule: '<a|b>'>
|
||
|
|
<StripRule: '<a|b>'>
|
||
|
|
<UnChunkRule: '<a|b>'>
|
||
|
|
<MergeRule: '<a>', '<b>'>
|
||
|
|
<SplitRule: '<a>', '<b>'>
|
||
|
|
<ExpandLeftRule: '<a>', '<b>'>
|
||
|
|
<ExpandRightRule: '<a>', '<b>'>
|
||
|
|
|
||
|
|
`tag_pattern2re_pattern()` complains if the tag pattern looks problematic:
|
||
|
|
|
||
|
|
>>> tag_pattern2re_pattern('{}')
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Bad tag pattern: '{}'
|
||
|
|
|
||
|
|
RegexpChunkParser
|
||
|
|
-----------------
|
||
|
|
|
||
|
|
A warning is printed when parsing an empty sentence:
|
||
|
|
|
||
|
|
>>> parser = RegexpChunkParser([ChunkRule('<a>', '')])
|
||
|
|
>>> parser.parse(Tree('S', []))
|
||
|
|
Warning: parsing empty text
|
||
|
|
Tree('S', [])
|
||
|
|
|
||
|
|
RegexpParser
|
||
|
|
------------
|
||
|
|
|
||
|
|
>>> parser = RegexpParser('''
|
||
|
|
... NP: {<DT>? <JJ>* <NN>*} # NP
|
||
|
|
... P: {<IN>} # Preposition
|
||
|
|
... V: {<V.*>} # Verb
|
||
|
|
... PP: {<P> <NP>} # PP -> P NP
|
||
|
|
... VP: {<V> <NP|PP>*} # VP -> V (NP|PP)*
|
||
|
|
... ''')
|
||
|
|
>>> print(repr(parser))
|
||
|
|
<chunk.RegexpParser with 5 stages>
|
||
|
|
>>> print(parser)
|
||
|
|
chunk.RegexpParser with 5 stages:
|
||
|
|
RegexpChunkParser with 1 rules:
|
||
|
|
NP <ChunkRule: '<DT>? <JJ>* <NN>*'>
|
||
|
|
RegexpChunkParser with 1 rules:
|
||
|
|
Preposition <ChunkRule: '<IN>'>
|
||
|
|
RegexpChunkParser with 1 rules:
|
||
|
|
Verb <ChunkRule: '<V.*>'>
|
||
|
|
RegexpChunkParser with 1 rules:
|
||
|
|
PP -> P NP <ChunkRule: '<P> <NP>'>
|
||
|
|
RegexpChunkParser with 1 rules:
|
||
|
|
VP -> V (NP|PP)* <ChunkRule: '<V> <NP|PP>*'>
|
||
|
|
>>> print(parser.parse(unchunked_text, trace=True))
|
||
|
|
# Input:
|
||
|
|
<DT> <NN> <VBD> <IN> <DT> <NN> <DT> <NN> <VBD> <.>
|
||
|
|
# NP:
|
||
|
|
{<DT> <NN>} <VBD> <IN> {<DT> <NN>}{<DT> <NN>} <VBD> <.>
|
||
|
|
# Input:
|
||
|
|
<NP> <VBD> <IN> <NP> <NP> <VBD> <.>
|
||
|
|
# Preposition:
|
||
|
|
<NP> <VBD> {<IN>} <NP> <NP> <VBD> <.>
|
||
|
|
# Input:
|
||
|
|
<NP> <VBD> <P> <NP> <NP> <VBD> <.>
|
||
|
|
# Verb:
|
||
|
|
<NP> {<VBD>} <P> <NP> <NP> {<VBD>} <.>
|
||
|
|
# Input:
|
||
|
|
<NP> <V> <P> <NP> <NP> <V> <.>
|
||
|
|
# PP -> P NP:
|
||
|
|
<NP> <V> {<P> <NP>} <NP> <V> <.>
|
||
|
|
# Input:
|
||
|
|
<NP> <V> <PP> <NP> <V> <.>
|
||
|
|
# VP -> V (NP|PP)*:
|
||
|
|
<NP> {<V> <PP> <NP>}{<V>} <.>
|
||
|
|
(S
|
||
|
|
(NP The/DT cat/NN)
|
||
|
|
(VP
|
||
|
|
(V sat/VBD)
|
||
|
|
(PP (P on/IN) (NP the/DT mat/NN))
|
||
|
|
(NP the/DT dog/NN))
|
||
|
|
(VP (V chewed/VBD))
|
||
|
|
./.)
|
||
|
|
|
||
|
|
Test parsing of other rule types:
|
||
|
|
|
||
|
|
>>> print(RegexpParser('''
|
||
|
|
... X:
|
||
|
|
... }<a><b>{ # strip rule
|
||
|
|
... <a>}{<b> # split rule
|
||
|
|
... <a>{}<b> # merge rule
|
||
|
|
... <a>{<b>}<c> # chunk rule w/ context
|
||
|
|
... '''))
|
||
|
|
chunk.RegexpParser with 1 stages:
|
||
|
|
RegexpChunkParser with 4 rules:
|
||
|
|
strip rule <StripRule: '<a><b>'>
|
||
|
|
split rule <SplitRule: '<a>', '<b>'>
|
||
|
|
merge rule <MergeRule: '<a>', '<b>'>
|
||
|
|
chunk rule w/ context <ChunkRuleWithContext: '<a>', '<b>', '<c>'>
|
||
|
|
|
||
|
|
Illegal patterns give an error message:
|
||
|
|
|
||
|
|
>>> print(RegexpParser('X: {<foo>} {<bar>}'))
|
||
|
|
Traceback (most recent call last):
|
||
|
|
. . .
|
||
|
|
ValueError: Illegal chunk pattern: {<foo>} {<bar>}
|