Aguila-team / Chinese_nlu_by_using_rasa_nlu
使用 RASA NLU 来构建中文自然语言理解系统(NLU)| Use RASA NLU to build a Chinese Natural Language Understanding System (NLU)
Stars: ✭ 99
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Chinese nlu by using rasa nlu
Awesome Hungarian Nlp
A curated list of NLP resources for Hungarian
Stars: ✭ 121 (+22.22%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Gluon Nlp
NLP made easy
Stars: ✭ 2,344 (+2267.68%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Spokestack Python
Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application.
Stars: ✭ 103 (+4.04%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Articutapi
API of Articut 中文斷詞 (兼具語意詞性標記):「斷詞」又稱「分詞」,是中文資訊處理的基礎。Articut 不用機器學習,不需資料模型,只用現代白話中文語法規則,即能達到 SIGHAN 2005 F1-measure 94% 以上,Recall 96% 以上的成績。
Stars: ✭ 252 (+154.55%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Botlibre
An open platform for artificial intelligence, chat bots, virtual agents, social media automation, and live chat automation.
Stars: ✭ 412 (+316.16%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Nlp Recipes
Natural Language Processing Best Practices & Examples
Stars: ✭ 5,783 (+5741.41%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Dialogflow Ruby Client
Ruby SDK for Dialogflow
Stars: ✭ 148 (+49.49%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Oie Resources
A curated list of Open Information Extraction (OIE) resources: papers, code, data, etc.
Stars: ✭ 283 (+185.86%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Clause
🏇 聊天机器人,自然语言理解,语义理解
Stars: ✭ 323 (+226.26%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Chat
基于自然语言理解与机器学习的聊天机器人,支持多用户并发及自定义多轮对话
Stars: ✭ 516 (+421.21%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Spark Nlp Models
Models and Pipelines for the Spark NLP library
Stars: ✭ 88 (-11.11%)
Mutual labels: natural-language-processing, natural-language-understanding, nlu
Mongolian Bert
Pre-trained Mongolian BERT models
Stars: ✭ 21 (-78.79%)
Mutual labels: natural-language-processing, natural-language-understanding
Max Text Sentiment Classifier
Detect the sentiment captured in short pieces of text
Stars: ✭ 35 (-64.65%)
Mutual labels: natural-language-processing, natural-language-understanding
Gsoc2018 3gm
💫 Automated codification of Greek Legislation with NLP
Stars: ✭ 36 (-63.64%)
Mutual labels: natural-language-processing, natural-language-understanding
Coursera Natural Language Processing Specialization
Programming assignments from all courses in the Coursera Natural Language Processing Specialization offered by deeplearning.ai.
Stars: ✭ 39 (-60.61%)
Mutual labels: natural-language-processing, natural-language-understanding
Ciff
Cornell Instruction Following Framework
Stars: ✭ 23 (-76.77%)
Mutual labels: natural-language-processing, natural-language-understanding
Reading comprehension tf
Machine Reading Comprehension in Tensorflow
Stars: ✭ 37 (-62.63%)
Mutual labels: natural-language-processing, natural-language-understanding
Blocks
Blocks World -- Simulator, Code, and Models (Misra et al. EMNLP 2017)
Stars: ✭ 39 (-60.61%)
Mutual labels: natural-language-processing, natural-language-understanding
Convai Baseline
ConvAI baseline solution
Stars: ✭ 49 (-50.51%)
Mutual labels: natural-language-processing, natural-language-understanding
Python Tutorial Notebooks
Python tutorials as Jupyter Notebooks for NLP, ML, AI
Stars: ✭ 52 (-47.47%)
Mutual labels: natural-language-processing, natural-language-understanding
README written in English
使用 RASA NLU 来构建中文自然语言理解系统(NLU)
本仓库提供前沿、详细和完备的中文自然语言理解系统构建指南。
在线演示
TODO
特性
- 提供中文语料库
- 提供语料库转换工具,帮助用户转移语料数据
- 提供多种基于 RASA NLU 的中文语言处理流程
- 提供模型性能评测工具,帮助自动选择和优化模型
系统要求
Python 3 (也许支持 python2, 但未经过良好测试)
处理流程
详情请访问 workflow.md
可用 pipeline 列表
MITIE+jieba
描述
- jieba 提供中文分词功能
- MITIE 负责
intent classification
和slot filling
安装依赖的软件包
pip install git+https://github.com/mit-nlp/MITIE.git
pip install jieba
下载所需的模型数据
MITIE 需要一个模型文件,在本人的另一个项目: MITIE_Chinese_Wikipedia_corpus 的 release 下载 total_word_feature_extractor.dat.tar.gz
. 解压后将 total_word_feature_extractor.dat
放至 data
pipeline
language: "zh"
pipeline:
- name: "nlp_mitie"
model: "data/total_word_feature_extractor.dat"
- name: "tokenizer_jieba"
- name: "ner_mitie"
- name: "ner_synonyms"
- name: "intent_featurizer_mitie"
- name: "intent_classifier_sklearn"
训练脚本
trainer/MITIE+jieba.bash
评估脚本
cross_validation/MITIE+jieba.bash
tensorflow_embedding
描述
- jieba 提供中文分词功能
- tensorflow_embedding 负责
intent classification
- MITIE 负责
slot filling
安装依赖的软件包
pip install git+https://github.com/mit-nlp/MITIE.git
pip install jieba
pip install tensorflow
下载所需的模型数据
MITIE 需要一个模型文件,在本人的另一个项目: MITIE_Chinese_Wikipedia_corpus 的 release 下载 total_word_feature_extractor.dat.tar.gz
. 解压后将 total_word_feature_extractor.dat
放至 data
pipeline
language: "zh"
pipeline:
- name: "nlp_mitie"
model: "data/total_word_feature_extractor.dat"
- name: "tokenizer_jieba"
- name: "intent_featurizer_count_vectors"
- name: "intent_classifier_tensorflow_embedding"
- name: "ner_mitie"
- name: "ner_synonyms"
训练脚本
trainer/tensorflow_embedding.bash
评估脚本
cross_validation/tensorflow_embedding.bash
spacy
描述
-
Chinese_models_for_SpaCy 负责
intent classification
andslot filling
安装依赖的软件包
pip install https://github.com/howl-anderson/Chinese_models_for_SpaCy/releases/download/v2.0.3/zh_core_web_sm-2.0.3.tar.gz
./spacy_model_link.bash
pipeline
language: "zh"
pipeline:
- name: "nlp_spacy"
model: "zh"
- name: "tokenizer_spacy"
- name: "intent_entity_featurizer_regex"
- name: "intent_featurizer_spacy"
- name: "ner_crf"
- name: "ner_synonyms"
- name: "intent_classifier_sklearn"
训练脚本
trainer/spacy.bash
评估脚本
cross_validation/spacy.bash
性能测试
DialogFlow > weather
Intent | Entity | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
train | test | train | test | |||||||||
No | ACC | F1 | PRC | ACC | F1 | PRC | ACC | F1 | PRC | ACC | F1 | PRC |
1 | 0.986 | 0.986 | 0.986 | 0.665 | 0.631 | 0.648 | 0.987 | 0.987 | 0.988 | 0.967 | 0.968 | 0.973 |
2 | 0.990 | 0.990 | 0.990 | 0.434 | 0.406 | 0.432 | 0.987 | 0.987 | 0.988 | 0.968 | 0.970 | 0.975 |
3 | 0.992 | 0.992 | 0.992 | 0.657 | 0.598 | 0.587 | 0.987 | 0.987 | 0.988 | 0.939 | 0.934 | 0.947 |
ACC: Accuracy; F1: F1-score; PRC: Precision; |
Model List
No | Pipeline | Configure |
---|---|---|
1 | MITIE+jieba | 使用 MITIE_Chinese_Wikipedia_corpus 项目提供的 total_word_feature_extractor.dat
|
2 | tensorflow_embedding | 使用 MITIE_Chinese_Wikipedia_corpus 项目提供的 total_word_feature_extractor.dat
|
3 | spacy | 使用 Chinese_models_for_SpaCy 项目提供的中文 SpaCy 模型 |
如何贡献
请阅读 CONTRIBUTING.md , 然后提交 pull requests 给我们.
版本化控制
我们使用 SemVer 做版本化的标准. 查看 tags
以了解所有的版本.
作者
- Xiaoquan Kong - Initial work - howl-anderson
更多贡献者信息,请参考 contributors
.
版权
MIT License - 详见 LICENSE.md
致谢
- TODO
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].