spaCy 的 Matcher 与 PhraseMatcher

使用 spaCy 的自然语言处理

Azadeh Mobasher

Principal Data Scientist

spaCy 中的 Matcher

正则（RegEx）模式可能复杂、难读且难调试。
spaCy 提供可读、可用于生产的替代方案：Matcher 类。

import spacy
from spacy.matcher import Matcher

nlp = spacy.load("en_core_web_sm")
doc = nlp("Good morning, this is our first day on campus.")

matcher = Matcher(nlp.vocab)

spaCy 中的 Matcher

匹配结果包含匹配片段的起始与结束词元索引。

pattern = [{"LOWER": "good"}, {"LOWER": "morning"}]

matcher.add("morning_greeting", [pattern])

matches = matcher(doc)
for match_id, start, end in matches:
    print("Start token: ", start, " | End token: ", end, 
          "| Matched text: ", doc[start:end].text)

>>> Start token:  0  | End token:  2 | Matched text:  Good morning

Matcher 的扩展语法

定义匹配模式时可使用运算符。
与 Python 的 in、not in 和比较运算符类似

Attribute	Value type	Description
`IN`	any type	属性值属于列表
`NOT_IN`	any type	属性值不属于列表
`==`, `>=`, `<=`, `>`, `<`	int, float	用于相等/不等比较的运算符

Matcher 的扩展语法

使用 IN 运算符同时匹配 good morning 与 good evening

doc = nlp("Good morning and good evening.")
matcher = Matcher(nlp.vocab)
pattern = [{"LOWER": "good"}, {"LOWER": {"IN": ["morning", "evening"]}}]
matcher.add("morning_greeting", [pattern])
matches = matcher(doc)

使用 IN 的匹配输出

for match_id, start, end in matches:
    print("Start token: ", start, " | End token: ", end,
          "| Matched text: ", doc[start:end].text)

>>> Start token:  0  | End token:  2 | Matched text:  Good morning
Start token:  3  | End token:  5 | Matched text:  good evening

spaCy 中的 PhraseMatcher

PhraseMatcher 类用于在文本中匹配大量短语。

from spacy.matcher import PhraseMatcher
nlp = spacy.load("en_core_web_sm")
matcher = PhraseMatcher(nlp.vocab)
terms = ["Bill Gates", "John Smith"]

spaCy 中的 PhraseMatcher

PhraseMatcher 的输出包含匹配片段的起始与结束词元索引

patterns = [nlp.make_doc(term) for term in terms]
matcher.add("PeopleOfInterest", patterns)

doc = nlp("Bill Gates met John Smith for an important discussion regarding 
           importance of AI.")

matches = matcher(doc)
for match_id, start, end in matches:
    print("Start token: ", start, " | End token: ", end, 
          "| Matched text: ", doc[start:end].text)

>>> Start token:  0  | End token:  2 | Matched text:  Bill Gates
Start token:  3  | End token:  5 | Matched text:  John Smith

spaCy 中的 PhraseMatcher

可使用 PhraseMatcher 的 attr 参数

matcher = PhraseMatcher(nlp.vocab, attr = "LOWER")

terms = ["Government", "Investment"]
patterns = [nlp.make_doc(term) for term in terms]
matcher.add("InvestmentTerms", patterns)
doc = nlp("It was interesting to the investment division of the government.")

matcher = PhraseMatcher(nlp.vocab, attr = "SHAPE")

terms = ["110.0.0.0", "101.243.0.0"]
patterns = [nlp.make_doc(term) for term in terms]
matcher.add("IPAddresses", patterns)
doc = nlp("The tracked IP address was 234.135.0.0.")

Passons à la pratique !

使用 spaCy 的自然语言处理