https://github.com/mvollrath/nlu_examples
Examples accompanying an NLU presentation.
https://github.com/mvollrath/nlu_examples
ai example machine-learning nlp nlu
Last synced: about 1 year ago
JSON representation
Examples accompanying an NLU presentation.
- Host: GitHub
- URL: https://github.com/mvollrath/nlu_examples
- Owner: mvollrath
- Created: 2017-10-30T07:12:48.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-11-15T00:37:50.000Z (over 8 years ago)
- Last Synced: 2025-01-08T08:45:37.294Z (about 1 year ago)
- Topics: ai, example, machine-learning, nlp, nlu
- Language: Shell
- Size: 5.86 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
NLU Examples
------------
### Basic
An example of an extremely primitive neural network NLU classifier made with [Keras](https://keras.io/).
The purpose of this example is to demonstrate a supervised machine learning NLU in a setting limited enough that a working network can be solved with pencil and paper.
To run this example in Docker, use `run_basic.sh`. Sources are in `examples/basic`.
### Rasa
An example of intent classification and entity extraction with [Rasa NLU](https://github.com/RasaHQ/rasa_nlu).
The purpose of this example is to demonstrate a full-featured NLU implementation stack from training data to web front-end. A web form recognizes requests for food and random numbers in a given range.
For example, it will recognize "i want some pizza" as a food craving (for pizza) and "random number between 1 and 100" as a random number request (between 1 and 100, inclusive).
To run this example in Docker, use `run_rasa.sh`. The application will be listening on . Sources and training data are in `examples/rasa`.
### [Slides](https://docs.google.com/presentation/d/1gHRVUvyYcAvfx4dyoTU-zh3Msf5o-HqYvtL5ilP3djM/edit?usp=sharing)