https://github.com/howl-anderson/rasa_contrib
rasa_contrib is a addon package for rasa. It provide some useful/powerful addition components
https://github.com/howl-anderson/rasa_contrib
addons components contrib paddlepaddle rasa tensorflow
Last synced: 8 months ago
JSON representation
rasa_contrib is a addon package for rasa. It provide some useful/powerful addition components
- Host: GitHub
- URL: https://github.com/howl-anderson/rasa_contrib
- Owner: howl-anderson
- License: apache-2.0
- Created: 2019-04-22T12:43:18.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2022-12-08T05:15:28.000Z (over 3 years ago)
- Last Synced: 2024-09-27T13:41:03.218Z (over 1 year ago)
- Topics: addons, components, contrib, paddlepaddle, rasa, tensorflow
- Language: Python
- Homepage:
- Size: 6.7 MB
- Stars: 21
- Watchers: 4
- Forks: 3
- Open Issues: 17
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# rasa_contrib
rasa_contrib is a addon package for [rasa](https://github.com/RasaHQ/rasa). It provide some useful/powerful addition component.
## component
Currently, it includes:
* addons_intent_classifier_textcnn_tf
TextCNN based intent classifier, based on TensorFlow
* addons_intent_classifier_textcnn_paddle
TextCNN based intent classifier, based on PaddlePaddle
* addons_ner_bilstm_crf_tf
Embedding+BiLSTM+CRF based NER extractor, based on TensorFlow
* addons_ner_bilstm_crf_paddle
Embedding+BiLSTM+CRF based NER extractor, based on PaddlePaddle
* bert_text_featurizer
get BERT-based text vector feature
* bert_char_featurizer
get BERT-based char/word vector feature
It also includes (but still work in progress):
* MicroAddonsTokenizer
Chinese tokenizer component, based on [MicroTokenizer](https://github.com/howl-anderson/MicroTokenizer)
* StackedBilstmTensorFlowPolicy
Stacked Bilstm based dialog policy, based on TensorFlow
* StackedBilstmPaddlePolicy
Stacked Bilstm based dialog policy, based on PaddlePaddle
## how to use it
Using the class path to the place where you should given a component name in config.yaml. This is a feature of rasa, see here for more document from rasa official document.
For example, your config.yml can be:
```yaml
language: "zh"
pipeline:
- name: "rasa_contrib.nlu..TensorflowNLP"
- name: "rasa_contrib.nlu..BilstmCrfTensorFlowEntityExtractor"
max_steps: 600
- name: "rasa_contrib.nlu.TextCnnTensorFlowClassifier"
max_steps: 600
policies:
- name: MemoizationPolicy
- name: rasa_contrib.core.StackedBilstmTensorFlowPolicy
```