spaCy 的 Matcher 與 PhraseMatcher

使用 spaCy 的自然語言處理

Azadeh Mobasher

Principal Data Scientist

spaCy 的 Matcher

RegEx 模式常很複雜，難以閱讀與除錯。
spaCy 提供可讀、可用於正式環境的替代方案：Matcher 類別。

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 的 Matcher

比對輸出包含相符樣式的 start 與 end 標記索引。

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 進階語法支援

可在樣式中使用運算子。
與 Python 的 in、not in 與比較運算子相似。

Attribute	Value type	Description
`IN`	any type	屬性值為清單成員
`NOT_IN`	any type	屬性值「不」屬於清單成員
`==`, `>=`, `<=`, `>`, `<`	int, float	相等與不等的比較運算

Matcher 進階語法支援

使用 IN 運算子同時比對 good morning 與 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 運算子的比對輸出

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 的 PhraseMatcher

PhraseMatcher 類別可在文字中比對長清單的片語。

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

spaCy 的 PhraseMatcher

PhraseMatcher 的輸出包含相符樣式的 start 與 end 標記索引。

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 的 PhraseMatcher

可使用 PhraseMatcher 類別的 attr 參數。

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.")

一起來練習吧！

使用 spaCy 的自然語言處理