基于pytorch使用wmd实现句子语义匹配算法_python wmd-relax

1. 安装相关包

（1）spacy

github地址：https://github.com/explosion/spaCy

pip install spacy
python -m spacy download en_core_web_sm # 安装模型包
python -m spacy download en_core_web_md # 安装模型包
1
2
3

（2）wmd

github地址：https://github.com/src-d/wmd-relax

pip install wmd
1

2. Python Demo

(1) 使用spacy加载模型

import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")
1
2
3

（2）使用wmd计算两个句子的wmd匹配程度

import numpy
import spacy
from wmd import WMD

nlp = spacy.load('en_core_web_md')
doc1 = nlp("Politician speaks to the media in Illinois.")
doc2 = nlp("The president greets the press in Chicago.")
print(doc1.similarity(doc2))
1
2
3
4
5
6
7
8