/snips-nlu-rs

Snips NLU rust implementation

Primary LanguageRustOtherNOASSERTION

Snips NLU Rust

https://travis-ci.org/snipsco/snips-nlu-rs.svg?branch=develop https://ci.appveyor.com/api/projects/status/rsf27a9txeomic8o/branch/develop?svg=true

Installation

Add it to your Cargo.toml:

[dependencies]
snips-nlu-lib = { git = "https://github.com/snipsco/snips-nlu-rs", branch = "master" }

Add extern crate snips_nlu_lib to your crate root and you are good to go!

Intent Parsing with Snips NLU

The purpose of the main crate of this repository, snips-nlu-lib, is to perform an information extraction task called intent parsing.

Let’s take an example to illustrate the main purpose of this lib, 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",
      "confidenceScore": 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 order to achieve such a result, the NLU engine needs to be fed with a trained model (json file). This repository only contains the inference part, in order to produce trained models please check the Snips NLU python library.

Example and API Usage

The interactive parsing CLI is a good example of to how to use snips-nlu-rs.

Here is how you can run the CLI example:

$ git clone https://github.com/snipsco/snips-nlu-rs
$ cd snips-nlu-rs
$ cargo run --example interactive_parsing_cli data/tests/models/nlu_engine

Here we used a sample trained engine, which consists in two intents: MakeCoffee and MakeTea. Thus, it will be able to parse queries like "Make me two cups of coffee please" or "I'd like a hot tea".

As mentioned in the previous section, you can train your own nlu engine with the Snips NLU python library.

License

Licensed under either of

at your option.

Contribution

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.