pattern match for nlp
Project description
说明
支持中文语句的模版匹配。可以理解为,简单版本的百度unit或者科大讯飞的AIUI
对于,简单语句的自然语言理解也是很方便的。欢迎大家试用。
对于不喜欢调用API,喜欢在自己代码中嵌入的人是蛮好用的。
用例
```
from pmnlp.word import build_sentence_word_dict
from pmnlp.sentence import SentenceTplTrie
# 初始化,用于记录用户配置的词槽,以及语句的模版匹配。
user_word_dict = {'num': ['一杯', '两杯'], 'coffee': [
'拿铁', '拿铁咖啡'], 'common': [], 'phone': ['re\d+']}
sentent_intent_tpl = {
'coffee': '[common:0-4][num][common:0-10][coffee]'
}
# 建立模型
sentence_word_dict = build_sentence_word_dict(word_dict=user_word_dict)
test_tree = SentenceTplTrie(word_dict=sentence_word_dict)
test_tree.build(sentence_tpl_dict=sentent_intent_tpl, common_key='common')
# 理解用户输入
_, intent, result = test_tree.sep('我要一杯热啊啊啊啊啊啊拿铁咖啡',common_key='common')
if isinstance(intent, str):
print(intent, result)
else:
print(intent, result)
```
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pmnlp-0.2.0.tar.gz
(5.1 kB
view details)
File details
Details for the file pmnlp-0.2.0.tar.gz.
File metadata
- Download URL: pmnlp-0.2.0.tar.gz
- Upload date:
- Size: 5.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
25b7c17334ec66a866c0c7eb12f519ff40708246e072897696cd2e3f19a15c62
|
|
| MD5 |
7f3d9cb350dd3cc0ff1527ee48e011ad
|
|
| BLAKE2b-256 |
1499f66f014450344251e68129a3753c6fcf31b1bda8170a6550676162612bb9
|