一、Chatbot_NLU
Chatbot_NLU 是一个基于 RASA 的自定义中文语言理解组件,他可以替换掉RASA中本身的nlu模块,可以使nlu的准确率有较大提升,目前 引入了 bert ,后续将引入 xlnet 。
同时,RASA 的自定义组件可以参考 Custom NLU Components
目前 Chatbot_NLU 支持的功能有:
1、bert vector
2、bert intent
3、bert slot
二、安装使用
1、安装
pip install chatbot_nlu
2、使用
Chatbot_NLU 的使用是在 config.yml 文件中修改配置,常见的使用方法请参考:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "chatbot_nlu.extractors.crf_entity_extractor.CRFEntityExtractor"
# ner
- name: "chatbot_nlu.extractors.jieba_pseg_extractor.JiebaPsegExtractor"
part_of_speech: ["nr"]
- name: "chatbot_nlu.extractors.bilstm_crf_entity_extractor.BilstmCRFEntityExtractor"
# Word Embedding
- name: "chatbot_nlu.featurizers.bert_vectors_featurizer.BertVectorsFeaturizer"
ip: "172.18.103.43"
port: 5555
port_out: 5556
show_server_config: True
timeout: 10000
check_version: False
三、Update News
2020.1.7 接入钉钉群,支持主动推送消息、outgoing交互
2020.1.9 接入微信
四、Resources
Metadata
Release files for chatbot-nlu 1.0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| chatbot_nlu-1.0.3-py3-none-any.whl | Python 3 | none | any | Details |
Release files / chatbot_nlu-1.0.3-py3-none-any.whl
| Download URL | chatbot_nlu-1.0.3-py3-none-any.whl |
|---|---|
| Size | 191.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
295d56e3ffb2a13aa5eb0f029f61a43487bd970e06c7d503b812654c61bf5126
|
|
BLAKE2b-256 checksum How to use checksums |
d6eff336e78f72ca1667bb1211aac2b1184294013000f578b1d72ee0c5b0a12e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.4.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4
|
Security for chatbot-nlu 1.0.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.