Spaces:
Sleeping
Sleeping
File size: 1,946 Bytes
d916065 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
# Natural Language Toolkit: Chunk parsing API
#
# Copyright (C) 2001-2023 NLTK Project
# Author: Edward Loper <[email protected]>
# Steven Bird <[email protected]> (minor additions)
# URL: <https://www.nltk.org/>
# For license information, see LICENSE.TXT
##//////////////////////////////////////////////////////
## Chunk Parser Interface
##//////////////////////////////////////////////////////
from nltk.chunk.util import ChunkScore
from nltk.internals import deprecated
from nltk.parse import ParserI
class ChunkParserI(ParserI):
"""
A processing interface for identifying non-overlapping groups in
unrestricted text. Typically, chunk parsers are used to find base
syntactic constituents, such as base noun phrases. Unlike
``ParserI``, ``ChunkParserI`` guarantees that the ``parse()`` method
will always generate a parse.
"""
def parse(self, tokens):
"""
Return the best chunk structure for the given tokens
and return a tree.
:param tokens: The list of (word, tag) tokens to be chunked.
:type tokens: list(tuple)
:rtype: Tree
"""
raise NotImplementedError()
@deprecated("Use accuracy(gold) instead.")
def evaluate(self, gold):
return self.accuracy(gold)
def accuracy(self, gold):
"""
Score the accuracy of the chunker against the gold standard.
Remove the chunking the gold standard text, rechunk it using
the chunker, and return a ``ChunkScore`` object
reflecting the performance of this chunk parser.
:type gold: list(Tree)
:param gold: The list of chunked sentences to score the chunker on.
:rtype: ChunkScore
"""
chunkscore = ChunkScore()
for correct in gold:
chunkscore.score(correct, self.parse(correct.leaves()))
return chunkscore
|