Snips NLU (Natural Language Understanding) is a Python library that allows to parse sentences written in natural language and extracts structured information.
Summary
What is Snips NLU about ?
Behind every chatbot and voice assistant lies a common piece of technology: Natural Language Understanding (NLU). Anytime a user interacts with an AI using natural language, their words need to be translated into a machine-readable description of what they meant.
The NLU engine first detects what the intention of the user is (a.k.a. intent), then extracts the parameters (called slots) of the query. The developer can then use this to determine the appropriate action or response.
Let’s take an example to illustrate this, and consider the following sentence:
"What will be the weather in paris at 9pm?"Properly trained, the Snips NLU engine will be able to extract structured data such as:
{
"intent": {
"intentName": "searchWeatherForecast",
"probability": 0.95
},
"slots": [
{
"value": "paris",
"entity": "locality",
"slotName": "forecast_locality"
},
{
"value": {
"kind": "InstantTime",
"value": "2018-02-08 20:00:00 +00:00"
},
"entity": "snips/datetime",
"slotName": "forecast_start_datetime"
}
]
}In this case, the identified intent is searchWeatherForecast and two slots were extracted, a locality and a datetime. As you can see, Snips NLU does an extra step on top of extracting entities: it resolves them. The extracted datetime value has indeed been converted into a handy ISO format.
Check out our blog post to get more details about why we built Snips NLU and how it works under the hood. We also published a paper on arxiv, presenting the machine learning architecture of the Snips Voice Platform.
Getting Started
System requirements
Python 2.7 or Python >= 3.4, < 3.7
RAM: Snips NLU will typically use between 100MB and 200MB of RAM, depending on the language and the size of the dataset.
Installation
pip install snips-nluWe currently have pre-built binaries (wheels) for snips-nlu and its dependencies for MacOS (10.11 and later), Linux x86_64 and Windows.
For any other architecture/os snips-nlu can be installed from the source distribution. To do so, Rust and setuptools_rust must be installed before running the pip install snips-nlu command.
Language resources
Snips NLU relies on external language resources that must be downloaded before the library can be used. You can fetch resources for a specific language by running the following command:
python -m snips_nlu download enOr simply:
snips-nlu download enOnce the resources have been fetched, they can be loaded in Python using:
from snips_nlu import load_resources
load_resources("en")The list of supported languages is available at this address.
API Usage
Command Line Interface
The easiest way to test the abilities of this library is through the command line interface.
First, start by training the NLU with one of the sample datasets:
snips-nlu train path/to/dataset.json path/to/output_trained_engineWhere path/to/dataset.json is the path to the dataset which will be used during training, and path/to/output_trained_engine is the location where the trained engine should be persisted once the training is done.
After that, you can start parsing sentences interactively by running:
snips-nlu parse path/to/trained_engineWhere path/to/trained_engine corresponds to the location where you have stored the trained engine during the previous step.
Sample code
Here is a sample code that you can run on your machine after having installed snips-nlu, fetched the english resources and downloaded one of the sample datasets:
from __future__ import unicode_literals, print_function
import io
import json
from snips_nlu import SnipsNLUEngine, load_resources
from snips_nlu.default_configs import CONFIG_EN
with io.open("sample_dataset.json") as f:
sample_dataset = json.load(f)
load_resources("en")
nlu_engine = SnipsNLUEngine(config=CONFIG_EN)
nlu_engine.fit(sample_dataset)
text = "What will be the weather in San Francisco next week?"
parsing = nlu_engine.parse(text)
print(json.dumps(parsing, indent=2))What it does is training an NLU engine on a sample weather dataset and parsing a weather query.
Sample datasets
Here is a list of some datasets that can be used to train a Snips NLU engine:
Lights dataset: “Turn on the lights in the kitchen”, “Set the light to red in the bedroom”
Beverage dataset: “Prepare two cups of cappucino”, “Make me a cup of tea”
Flights dataset: “Book me a flight to go to boston this weekend”, “book me some tickets from istanbul to moscow in three days”
Benchmarks
In January 2018, we reproduced an academic benchmark which was published during the summer 2017. In this article, authors assessed the performance of API.ai (now Dialogflow, Google), Luis.ai (Microsoft), IBM Watson, and Rasa NLU. For fairness, we used an updated version of Rasa NLU and compared it to the latest version of Snips NLU (both in dark blue).
In the figure above, F1 scores of both intent classification and slot filling were computed for several NLU providers, and averaged accross the three datasets used in the academic benchmark mentionned before. All the underlying results can be found here.
Documentation
To find out how to use Snips NLU please refer to the package documentation, it will provide you with a step-by-step guide on how to setup and use this library.
FAQ
Please join Snips Discord channel to ask your questions and get feedback from the community.
How do I contribute ?
Please see the Contribution Guidelines.
Licence
This library is provided by Snips as Open Source software. See LICENSE for more information.
2 maintainers
Metadata
2 maintainers
Release files for snips-nlu 0.17.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| snips_nlu-0.17.2.tar.gz | 70.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| snips_nlu-0.17.2-py2.py3-none-any.whl | Python 3, Python 2 | none | any | Details |
Total release size: 173.7 kB
Release files / snips_nlu-0.17.2.tar.gz
| Download URL | snips_nlu-0.17.2.tar.gz |
|---|---|
| Size | 70.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d9499f9ca9e8bf3890cf7a99e21c9c68ce4cb594a28232a1db68988a16b795f3
|
|
BLAKE2b-256 checksum How to use checksums |
93e105ab0203a5dd6db2faec97e511ce63e910f017a926a20986868ff10d95f9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/39.0.1 requests-toolbelt/0.8.0 tqdm/4.19.6 CPython/3.6.5
|
Release files / snips_nlu-0.17.2-py2.py3-none-any.whl
| Download URL | snips_nlu-0.17.2-py2.py3-none-any.whl |
|---|---|
| Size | 102.7 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
5cfc83fe85822a8aa18df57e7e9ac1fb49f15b9f5ec29a39d3b1cc22e5ec46be
|
|
BLAKE2b-256 checksum How to use checksums |
15239d3b3f0b09554dd1812f2cfed39b61c4ee65094474916eba068fbdd1cbf6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/39.0.1 requests-toolbelt/0.8.0 tqdm/4.19.6 CPython/3.6.5
|
