mirror of https://github.com/explosion/spaCy.git
224 lines
9.7 KiB
Plaintext
224 lines
9.7 KiB
Plaintext
//- 💫 DOCS > USAGE > DEPENDENCY PARSE
|
|
|
|
include ../../_includes/_mixins
|
|
|
|
p
|
|
| spaCy features a fast and accurate syntactic dependency parser, and has
|
|
| a rich API for navigating the tree. The parser also powers the sentence
|
|
| boundary detection, and lets you iterate over base noun phrases, or
|
|
| "chunks".
|
|
|
|
p
|
|
| You can check whether a #[+api("doc") #[code Doc]] object has been
|
|
| parsed with the #[code doc.is_parsed] attribute, which returns a boolean
|
|
| value. If this attribute is #[code False], the default sentence iterator
|
|
| will raise an exception.
|
|
|
|
+h(2, "noun-chunks") Noun chunks
|
|
+tag-model("dependency parse")
|
|
|
|
p Lorem ipsum dolor sit amet, consectetur adipiscing elit. Quisque enim ante, pretium a orci eget, varius dignissim augue. Nam eu dictum mauris, id tincidunt nisi. Integer commodo pellentesque tincidunt. Nam at turpis finibus tortor gravida sodales tincidunt sit amet est. Nullam euismod arcu in tortor auctor.
|
|
|
|
+code("Example").
|
|
nlp = spacy.load('en')
|
|
doc = nlp(u'Autonomous cars shift insurance liability toward manufacturers')
|
|
for chunk in doc.noun_chunks:
|
|
print(chunk.text, chunk.root.text, chunk.root.dep_,
|
|
chunk.root.head.text)
|
|
|
|
+aside
|
|
| #[strong Text:] The original noun chunk text.#[br]
|
|
| #[strong Root text:] ...#[br]
|
|
| #[strong Root dep:] ...#[br]
|
|
| #[strong Root head text:] ...#[br]
|
|
|
|
+table(["Text", "root.text", "root.dep_", "root.head.text"])
|
|
- var style = [0, 0, 1, 0]
|
|
+annotation-row(["Autonomous cars", "cars", "nsubj", "shift"], style)
|
|
+annotation-row(["insurance liability", "liability", "dobj", "shift"], style)
|
|
+annotation-row(["manufacturers", "manufacturers", "pobj", "toward"], style)
|
|
|
|
+h(2, "navigating") Navigating the parse tree
|
|
|
|
p
|
|
| spaCy uses the terms #[strong head] and #[strong child] to describe the words
|
|
| #[strong connected by a single arc] in the dependency tree. The term
|
|
| #[strong dep] is used for the arc label, which describes the type of
|
|
| syntactic relation that connects the child to the head. As with other
|
|
| attributes, the value of #[code .dep] is an integer. You can get
|
|
| the string value with #[code .dep_].
|
|
|
|
+code("Example").
|
|
doc = nlp(u'Autonomous cars shift insurance liability toward manufacturers')
|
|
for token in doc:
|
|
print(token.text, token.dep_, token.head.text, token.head.pos_,
|
|
[child for child in token.children])
|
|
|
|
+aside
|
|
| #[strong Text]: The original token text.#[br]
|
|
| #[strong Dep]: The syntactic relation connecting child to head.#[br]
|
|
| #[strong Head text]: The original text of the token head.#[br]
|
|
| #[strong Head POS]: The part-of-speech tag of the token head.#[br]
|
|
| #[strong Children]: ...
|
|
|
|
+table(["Text", "Dep", "Head text", "Head POS", "Children"])
|
|
- var style = [0, 1, 0, 1, 0]
|
|
+annotation-row(["Autonomous", "amod", "cars", "NOUN", ""], style)
|
|
+annotation-row(["cars", "nsubj", "shift", "VERB", "Autonomous"], style)
|
|
+annotation-row(["shift", "ROOT", "shift", "VERB", "cars, liability"], style)
|
|
+annotation-row(["insurance", "compound", "liability", "NOUN", ""], style)
|
|
+annotation-row(["liability", "dobj", "shift", "VERB", "insurance, toward"], style)
|
|
+annotation-row(["toward", "prep", "liability", "NOUN", "manufacturers"], style)
|
|
+annotation-row(["manufacturers", "pobj", "toward", "ADP", ""], style)
|
|
|
|
+codepen("dcf8d293367ca185b935ed2ca11ebedd", 370)
|
|
|
|
p
|
|
| Because the syntactic relations form a tree, every word has
|
|
| #[strong exactly one head]. You can therefore iterate over the arcs in
|
|
| the tree by iterating over the words in the sentence. This is usually
|
|
| the best way to match an arc of interest — from below:
|
|
|
|
+code.
|
|
from spacy.symbols import nsubj, VERB
|
|
|
|
# Finding a verb with a subject from below — good
|
|
verbs = set()
|
|
for possible_subject in doc:
|
|
if possible_subject.dep == nsubj and possible_subject.head.pos == VERB:
|
|
verbs.add(possible_subject.head)
|
|
|
|
p
|
|
| If you try to match from above, you'll have to iterate twice: once for
|
|
| the head, and then again through the children:
|
|
|
|
+code.
|
|
# Finding a verb with a subject from above — less good
|
|
verbs = []
|
|
for possible_verb in doc:
|
|
if possible_verb.pos == VERB:
|
|
for possible_subject in possible_verb.children:
|
|
if possible_subject.dep == nsubj:
|
|
verbs.append(possible_verb)
|
|
break
|
|
|
|
p
|
|
| To iterate through the children, use the #[code token.children]
|
|
| attribute, which provides a sequence of #[+api("token") #[code Token]]
|
|
| objects.
|
|
|
|
+h(3, "navigating-around") Iterating around the local tree
|
|
|
|
p
|
|
| A few more convenience attributes are provided for iterating around the
|
|
| local tree from the token. The #[code .lefts] and #[code .rights]
|
|
| attributes provide sequences of syntactic children that occur before and
|
|
| after the token. Both sequences are in sentences order. There are also
|
|
| two integer-typed attributes, #[code .n_rights] and #[code .n_lefts],
|
|
| that give the number of left and right children.
|
|
|
|
+code.
|
|
doc = nlp(u'bright red apples on the tree')
|
|
assert [token.text for token in doc[2].lefts]) == [u'bright', u'red']
|
|
assert [token.text for token in doc[2].rights]) == ['on']
|
|
assert doc[2].n_lefts == 2
|
|
assert doc[2].n_rights == 1
|
|
|
|
p
|
|
| You can get a whole phrase by its syntactic head using the
|
|
| #[code .subtree] attribute. This returns an ordered sequence of tokens.
|
|
| You can walk up the tree with the #[code .ancestors] attribute, and
|
|
| check dominance with the #[+api("token#is_ancestor") #[code .is_ancestor()]]
|
|
| method.
|
|
|
|
+aside("Projective vs. non-projective")
|
|
| For the #[+a("/docs/usage/models#available") default English model], the
|
|
| parse tree is #[strong projective], which means that there are no crossing
|
|
| brackets. The tokens returned by #[code .subtree] are therefore guaranteed
|
|
| to be contiguous. This is not true for the German model, which has many
|
|
| #[+a(COMPANY_URL + "/blog/german-model#word-order", true) non-projective dependencies].
|
|
|
|
+code.
|
|
doc = nlp(u'Credit and mortgage account holders must submit their requests')
|
|
root = [token for token in doc if token.head is token][0]
|
|
subject = list(root.lefts)[0]
|
|
for descendant in subject.subtree:
|
|
assert subject.is_ancestor(descendant)
|
|
print(descendant.text, descendant.dep_, descendant.n_lefts, descendant.n_rights,
|
|
[ancestor.text for ancestor in descendant.ancestors])
|
|
|
|
+table(["Text", "Dep", "n_lefts", "n_rights", "ancestors"])
|
|
- var style = [0, 1, 1, 1, 0]
|
|
+annotation-row(["Credit", "nmod", 0, 2, "holders, submit"], style)
|
|
+annotation-row(["and", "cc", 0, 0, "Credit, holders, submit"], style)
|
|
+annotation-row(["mortgage", "compound", 0, 0, "account, Credit, holders, submit"], style)
|
|
+annotation-row(["account", "conj", 1, 0, "Credit, holders, submit"], style)
|
|
+annotation-row(["holders", "nsubj", 1, 0, "submit"], style)
|
|
|
|
p
|
|
| Finally, the #[code .left_edge] and #[code .right_edge] attributes
|
|
| can be especially useful, because they give you the first and last token
|
|
| of the subtree. This is the easiest way to create a #[code Span] object
|
|
| for a syntactic phrase. Note that #[code .right_edge] gives a token
|
|
| #[strong within] the subtree — so if you use it as the end-point of a
|
|
| range, don't forget to #[code +1]!
|
|
|
|
+code.
|
|
doc = nlp(u'Credit and mortgage account holders must submit their requests')
|
|
span = doc[doc[4].left_edge.i : doc[4].right_edge.i+1]
|
|
span.merge()
|
|
for token in doc:
|
|
print(token.text, token.pos_, token.dep_, token.head.text)
|
|
|
|
+table(["Text", "POS", "Dep", "Head text"])
|
|
- var style = [0, 1, 1, 0]
|
|
+annotation-row(["Credit and mortgage account holders", "NOUN", "nsubj", "submit"], style)
|
|
+annotation-row(["must", "VERB", "aux", "submit"], style)
|
|
+annotation-row(["submit", "VERB", "ROOT", "submit"], style)
|
|
+annotation-row(["their", "ADJ", "poss", "requests"], style)
|
|
+annotation-row(["requests", "NOUN", "dobj", "submit"], style)
|
|
|
|
+h(2, "displacy") Visualizing dependencies
|
|
|
|
p
|
|
| The best way to understand spaCy's dependency parser is interactively.
|
|
| To make this easier, spaCy v2.0+ comes with a visualization module. Simply
|
|
| pass a #[code Doc] or a list of #[code Doc] objects to
|
|
| displaCy and run #[+api("displacy#serve") #[code displacy.serve]] to
|
|
| run the web server, or #[+api("displacy#render") #[code displacy.render]]
|
|
| to generate the raw markup. If you want to know how to write rules that
|
|
| hook into some type of syntactic construction, just plug the sentence into
|
|
| the visualizer and see how spaCy annotates it.
|
|
|
|
+code.
|
|
from spacy import displacy
|
|
|
|
doc = nlp(u'Autonomous cars shift insurance liability toward manufacturers')
|
|
displacy.serve(doc, style='dep')
|
|
|
|
+infobox
|
|
| For more details and examples, see the
|
|
| #[+a("/docs/usage/visualizers") usage workflow on visualizing spaCy]. You
|
|
| can also test displaCy in our #[+a(DEMOS_URL + "/displacy", true) online demo].
|
|
|
|
+h(2, "disabling") Disabling the parser
|
|
|
|
p
|
|
| The parser is loaded and enabled by default. If you don't need any of
|
|
| the syntactic information, you should disable the parser. Disabling the
|
|
| parser will make spaCy load and run much faster. Here's how to prevent
|
|
| the parser from being loaded:
|
|
|
|
+code.
|
|
nlp = spacy.load('en', parser=False)
|
|
|
|
p
|
|
| If you need to load the parser, but need to disable it for specific
|
|
| documents, you can control its use with the #[code parse] keyword
|
|
| argument:
|
|
|
|
+code.
|
|
nlp = spacy.load('en')
|
|
doc1 = nlp(u'Text I do want parsed.')
|
|
doc2 = nlp(u"Text I don't want parsed", parse=False)
|