pipeline/nltk/test/dependency.doctest

.. Copyright (C) 2001-2023 NLTK Project
.. For license information, see LICENSE.TXT

===================
Dependency Grammars
===================

    >>> from nltk.grammar import DependencyGrammar
    >>> from nltk.parse import (
    ...     DependencyGraph,
    ...     ProjectiveDependencyParser,
    ...     NonprojectiveDependencyParser,
    ... )

CoNLL Data
----------

    >>> treebank_data = """Pierre  NNP     2       NMOD
    ... Vinken  NNP     8       SUB
    ... ,       ,       2       P
    ... 61      CD      5       NMOD
    ... years   NNS     6       AMOD
    ... old     JJ      2       NMOD
    ... ,       ,       2       P
    ... will    MD      0       ROOT
    ... join    VB      8       VC
    ... the     DT      11      NMOD
    ... board   NN      9       OBJ
    ... as      IN      9       VMOD
    ... a       DT      15      NMOD
    ... nonexecutive    JJ      15      NMOD
    ... director        NN      12      PMOD
    ... Nov.    NNP     9       VMOD
    ... 29      CD      16      NMOD
    ... .       .       9       VMOD
    ... """

    >>> dg = DependencyGraph(treebank_data)
    >>> dg.tree().pprint()
    (will
      (Vinken Pierre , (old (years 61)) ,)
      (join (board the) (as (director a nonexecutive)) (Nov. 29) .))
    >>> for head, rel, dep in dg.triples():
    ...     print(
    ...         '({h[0]}, {h[1]}), {r}, ({d[0]}, {d[1]})'
    ...         .format(h=head, r=rel, d=dep)
    ...     )
    (will, MD), SUB, (Vinken, NNP)
    (Vinken, NNP), NMOD, (Pierre, NNP)
    (Vinken, NNP), P, (,, ,)
    (Vinken, NNP), NMOD, (old, JJ)
    (old, JJ), AMOD, (years, NNS)
    (years, NNS), NMOD, (61, CD)
    (Vinken, NNP), P, (,, ,)
    (will, MD), VC, (join, VB)
    (join, VB), OBJ, (board, NN)
    (board, NN), NMOD, (the, DT)
    (join, VB), VMOD, (as, IN)
    (as, IN), PMOD, (director, NN)
    (director, NN), NMOD, (a, DT)
    (director, NN), NMOD, (nonexecutive, JJ)
    (join, VB), VMOD, (Nov., NNP)
    (Nov., NNP), NMOD, (29, CD)
    (join, VB), VMOD, (., .)

Using a custom cell extractor.

    >>> def custom_extractor(cells):
    ...     _, tag, head, rel = cells
    ...     return 'spam', 'spam', tag, tag, '', head, rel
    >>> dg = DependencyGraph(treebank_data, cell_extractor=custom_extractor)
    >>> dg.tree().pprint()
    (spam
      (spam spam spam (spam (spam spam)) spam)
      (spam (spam spam) (spam (spam spam spam)) (spam spam) spam))

Custom cell extractors can take in and return an index.

    >>> def custom_extractor(cells, index):
    ...     word, tag, head, rel = cells
    ...     return (index, '{}-{}'.format(word, index), word,
    ...             tag, tag, '', head, rel)
    >>> dg = DependencyGraph(treebank_data, cell_extractor=custom_extractor)
    >>> dg.tree().pprint()
    (will-8
      (Vinken-2 Pierre-1 ,-3 (old-6 (years-5 61-4)) ,-7)
      (join-9
        (board-11 the-10)
        (as-12 (director-15 a-13 nonexecutive-14))
        (Nov.-16 29-17)
        .-18))

Using the dependency-parsed version of the Penn Treebank corpus sample.

    >>> from nltk.corpus import dependency_treebank
    >>> t = dependency_treebank.parsed_sents()[0]
    >>> print(t.to_conll(3))
    Pierre      NNP     2
    Vinken      NNP     8
    ,   ,       2
    61  CD      5
    years       NNS     6
    old JJ      2
    ,   ,       2
    will        MD      0
    join        VB      8
    the DT      11
    board       NN      9
    as  IN      9
    a   DT      15
    nonexecutive        JJ      15
    director    NN      12
    Nov.        NNP     9
    29  CD      16
    .   .       8

Using the output of zpar (like Malt-TAB but with zero-based indexing)

    >>> zpar_data = """
    ... Pierre	NNP	1	NMOD
    ... Vinken	NNP	7	SUB
    ... ,	,	1	P
    ... 61	CD	4	NMOD
    ... years	NNS	5	AMOD
    ... old	JJ	1	NMOD
    ... ,	,	1	P
    ... will	MD	-1	ROOT
    ... join	VB	7	VC
    ... the	DT	10	NMOD
    ... board	NN	8	OBJ
    ... as	IN	8	VMOD
    ... a	DT	14	NMOD
    ... nonexecutive	JJ	14	NMOD
    ... director	NN	11	PMOD
    ... Nov.	NNP	8	VMOD
    ... 29	CD	15	NMOD
    ... .	.	7	P
    ... """

    >>> zdg = DependencyGraph(zpar_data, zero_based=True)
    >>> print(zdg.tree())
    (will
      (Vinken Pierre , (old (years 61)) ,)
      (join (board the) (as (director a nonexecutive)) (Nov. 29))
      .)


Projective Dependency Parsing
-----------------------------

    >>> grammar = DependencyGrammar.fromstring("""
    ... 'fell' -> 'price' | 'stock'
    ... 'price' -> 'of' 'the'
    ... 'of' -> 'stock'
    ... 'stock' -> 'the'
    ... """)
    >>> print(grammar)
    Dependency grammar with 5 productions
      'fell' -> 'price'
      'fell' -> 'stock'
      'price' -> 'of' 'the'
      'of' -> 'stock'
      'stock' -> 'the'

    >>> dp = ProjectiveDependencyParser(grammar)
    >>> for t in sorted(dp.parse(['the', 'price', 'of', 'the', 'stock', 'fell'])):
    ...     print(t)
    (fell (price the (of (stock the))))
    (fell (price the of) (stock the))
    (fell (price the of the) stock)

Non-Projective Dependency Parsing
---------------------------------

    >>> grammar = DependencyGrammar.fromstring("""
    ... 'taught' -> 'play' | 'man'
    ... 'man' -> 'the'
    ... 'play' -> 'golf' | 'dog' | 'to'
    ... 'dog' -> 'his'
    ... """)
    >>> print(grammar)
    Dependency grammar with 7 productions
      'taught' -> 'play'
      'taught' -> 'man'
      'man' -> 'the'
      'play' -> 'golf'
      'play' -> 'dog'
      'play' -> 'to'
      'dog' -> 'his'

    >>> dp = NonprojectiveDependencyParser(grammar)
    >>> g, = dp.parse(['the', 'man', 'taught', 'his', 'dog', 'to', 'play', 'golf'])

    >>> print(g.root['word'])
    taught

    >>> for _, node in sorted(g.nodes.items()):
    ...     if node['word'] is not None:
    ...         print('{address} {word}: {d}'.format(d=node['deps'][''], **node))
    1 the: []
    2 man: [1]
    3 taught: [2, 7]
    4 his: []
    5 dog: [4]
    6 to: []
    7 play: [5, 6, 8]
    8 golf: []

    >>> print(g.tree())
    (taught (man the) (play (dog his) to golf))

Integration with MALT parser
============================

In case the top relation is different from the default, we can set it. In case
of MALT parser, it's set to `'null'`.

>>> dg_str = """1       I       _       NN      NN      _       2       nn      _       _
... 2   shot    _       NN      NN      _       0       null    _       _
... 3   an      _       AT      AT      _       2       dep     _       _
... 4   elephant        _       NN      NN      _       7       nn      _       _
... 5   in      _       NN      NN      _       7       nn      _       _
... 6   my      _       NN      NN      _       7       nn      _       _
... 7   pajamas _       NNS     NNS     _       3       dobj    _       _
... """
>>> dg = DependencyGraph(dg_str, top_relation_label='null')

>>> len(dg.nodes)
8

>>> dg.root['word'], dg.root['address']
('shot', 2)

>>> print(dg.to_conll(10))
1   I       _       NN      NN      _       2       nn      _       _
2   shot    _       NN      NN      _       0       null    _       _
3   an      _       AT      AT      _       2       dep     _       _
4   elephant        _       NN      NN      _       7       nn      _       _
5   in      _       NN      NN      _       7       nn      _       _
6   my      _       NN      NN      _       7       nn      _       _
7   pajamas _       NNS     NNS     _       3       dobj    _       _