GaoQ1 / Rasa_nlu_gq
Licence: apache-2.0
turn natural language into structured data(支持中文,自定义了N种模型,支持不同的场景和任务)
Stars: ✭ 256
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Rasa nlu gq
Nlp Recipes
Natural Language Processing Best Practices & Examples
Stars: ✭ 5,783 (+2158.98%)
Mutual labels: nlu, natural-language
gdpr-fingerprint-pii
Use Watson Natural Language Understanding and Watson Knowledge Studio to fingerprint personal data from unstructured documents
Stars: ✭ 49 (-80.86%)
Mutual labels: natural-language, nlu
fountain
Natural Language Data Augmentation Tool for Conversational Systems
Stars: ✭ 113 (-55.86%)
Mutual labels: natural-language, nlu
Botlibre
An open platform for artificial intelligence, chat bots, virtual agents, social media automation, and live chat automation.
Stars: ✭ 412 (+60.94%)
Mutual labels: nlu, natural-language
watson-document-classifier
Augment IBM Watson Natural Language Understanding APIs with a configurable mechanism for text classification, uses Watson Studio.
Stars: ✭ 41 (-83.98%)
Mutual labels: natural-language, nlu
nli-go
Natural Language Interface in GO, a semantic parser and execution engine.
Stars: ✭ 20 (-92.19%)
Mutual labels: natural-language
nlp-dialogue
A full-process dialogue system that can be deployed online
Stars: ✭ 69 (-73.05%)
Mutual labels: nlu
retext-profanities
plugin to check for profane and vulgar wording
Stars: ✭ 34 (-86.72%)
Mutual labels: natural-language
sepia-docs
Documentation and Wiki for SEPIA. Please post your questions and bug-reports here in the issues section! Thank you :-)
Stars: ✭ 160 (-37.5%)
Mutual labels: nlu
spokestack-android
Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
Stars: ✭ 52 (-79.69%)
Mutual labels: nlu
opensnips
Open source projects related to Snips https://snips.ai/.
Stars: ✭ 50 (-80.47%)
Mutual labels: nlu
array-to-sentence
Join all elements of an array and create a human-readable string
Stars: ✭ 32 (-87.5%)
Mutual labels: natural-language
expando
A simple syntax for defining the NLU model for a conversational interface.
Stars: ✭ 36 (-85.94%)
Mutual labels: nlu
apertium-html-tools
Web application providing a fully localised interface for text/website/document translation, analysis and generation powered by Apertium.
Stars: ✭ 36 (-85.94%)
Mutual labels: natural-language
react-taggy
A simple zero-dependency React component for tagging user-defined entities within a block of text.
Stars: ✭ 29 (-88.67%)
Mutual labels: natural-language
rita
Website, documentation and examples for RiTa
Stars: ✭ 42 (-83.59%)
Mutual labels: natural-language
Rasa NLU GQ
Rasa NLU (Natural Language Understanding) 是一个自然语义理解的工具,举个官网的例子如下:
"I'm looking for a Mexican restaurant in the center of town"
And returning structured data like:
intent: search_restaurant
entities:
- cuisine : Mexican
- location : center
Introduction
原来的项目在分支0.2.7上,可自由切换。这个版本的修改是基于最新版本的rasa,将原来rasa_nlu_gao里面的component修改了下,并没有做新增。并且之前做法有些累赘,并不需要在rasa源码中修改。可以直接将原来的component当做addon加载,继承最新版本的rasa,可实时更新。
New features
目前新增的特性如下(请下载最新的rasa-nlu-gao版本)(edit at 2019.06.24):
- 新增了实体识别的模型,一个是bilstm+crf,一个是idcnn+crf膨胀卷积模型,对应的yml文件配置如下:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "CountVectorsFeaturizer"
token_pattern: "(?u)\b\w+\b"
- name: "EmbeddingIntentClassifier"
- name: "rasa_nlu_gao.extractors.bilstm_crf_entity_extractor.BilstmCRFEntityExtractor"
lr: 0.001
char_dim: 100
lstm_dim: 100
batches_per_epoch: 10
seg_dim: 20
num_segs: 4
batch_size: 200
tag_schema: "iobes"
model_type: "bilstm" # 模型支持两种idcnn膨胀卷积模型或bilstm双向lstm模型
clip: 5
optimizer: "adam"
dropout_keep: 0.5
steps_check: 100
- 新增了jieba词性标注的模块,可以方便识别名字,地名,机构名等等jieba能够支持的词性,对应的yml文件配置如下:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "CRFEntityExtractor"
- name: "rasa_nlu_gao.extractors.jieba_pseg_extractor.JiebaPsegExtractor"
part_of_speech: ["nr", "ns", "nt"]
- name: "CountVectorsFeaturizer"
OOV_token: oov
token_pattern: "(?u)\b\w+\b"
- name: "EmbeddingIntentClassifier"
- 新增了根据实体反向修改意图,对应的文件配置如下:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "CRFEntityExtractor"
- name: "JiebaPsegExtractor"
- name: "CountVectorsFeaturizer"
OOV_token: oov
token_pattern: '(?u)\b\w+\b'
- name: "EmbeddingIntentClassifier"
- name: "rasa_nlu_gao.classifiers.entity_edit_intent.EntityEditIntent"
entity: ["nr"]
intent: ["enter_data"]
min_confidence: 0
- 新增了bert模型提取词向量特征,对应的配置文件如下:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "rasa_nlu_gao.featurizers.bert_vectors_featurizer.BertVectorsFeaturizer"
ip: '127.0.0.1'
port: 5555
port_out: 5556
show_server_config: True
timeout: 10000
- name: "EmbeddingIntentClassifier"
- name: "CRFEntityExtractor"
- 新增了对CPU和GPU的利用率的配置,主要是
EmbeddingIntentClassifier
和ner_bilstm_crf
这两个使用到tensorflow的组件,配置如下(当然config_proto可以不配置,默认值会将资源全部利用):
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "CountVectorsFeaturizer"
token_pattern: '(?u)\b\w+\b'
- name: "EmbeddingIntentClassifier"
config_proto: {
"device_count": 4,
"inter_op_parallelism_threads": 0,
"intra_op_parallelism_threads": 0,
"allow_growth": True
}
- name: "rasa_nlu_gao.extractors.bilstm_crf_entity_extractor.BilstmCRFEntityExtractor"
config_proto: {
"device_count": 4,
"inter_op_parallelism_threads": 0,
"intra_op_parallelism_threads": 0,
"allow_growth": True
}
- 新增了
embedding_bert_intent_classifier
分类器,对应的配置文件如下:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "rasa_nlu_gao.featurizers.bert_vectors_featurizer.BertVectorsFeaturizer"
ip: '127.0.0.1'
port: 5555
port_out: 5556
show_server_config: True
timeout: 10000
- name: "rasa_nlu_gao.classifiers.embedding_bert_intent_classifier.EmbeddingBertIntentClassifier"
- name: "CRFEntityExtractor"
- 在基础词向量使用bert的情况下,后端的分类器使用tensorflow高级api完成,tf.estimator,tf.data,tf.example,tf.saved_model
intent_estimator_classifier_tensorflow_embedding_bert
分类器,对应的配置文件如下:
language: "zh"
pipeline:
- name: "JiebaTokenizer"
- name: "rasa_nlu_gao.featurizers.bert_vectors_featurizer.BertVectorsFeaturizer"
ip: '127.0.0.1'
port: 5555
port_out: 5556
show_server_config: True
timeout: 10000
- name: "rasa_nlu_gao.classifiers.embedding_bert_intent_estimator_classifier.EmbeddingBertIntentEstimatorClassifier"
- name: "SpacyNLP"
- name: "CRFEntityExtractor"
- rasa-nlu的究极形态,对应的配置文件如下(edit at 2019.10.01)可参考上面的文章
Quick Install
pip install rasa-nlu-gao
Some Examples
具体的例子请看rasa_chatbot_cn
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].