[PR #1111] [CLOSED] Add Snips NLU library in Natural Language Processing section #995

New Issue

GiteaMirror · 2025-11-06T13:07:01-06:00

GiteaMirror commented

2025-11-06 13:07:01 -06:00

📋 Pull Request Information

Original PR: https://github.com/vinta/awesome-python/pull/1111
Author: @adrienball
Created: 8/17/2018
Status: ❌ Closed

Base: master ← Head: patch-1

📝 Commits (2)

4111e79 Add Snips NLU library in Natural Language Processing section
ca31408 Merge branch 'master' into patch-1

📊 Changes

1 file changed (+1 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)

📄 Description

What is this Python project?

Snips NLU is a natural language understanding library dedicated to Intent Parsing and Entity Extraction. It is based on machine learning and makes use of Logistic Regression and Conditional Random Fields.

Consider the following sentence:

    "What will be the weather in paris at 9pm?"

After proper training, the Snips NLU library allows 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"
          }
       ]
    }

What's the difference between this Python project and similar ones?

The purpose of Snips NLU is more high-level than libraries such as spaCy or NLTK and can be directly used to build chatbots for instance.
Snips NLU has been designed to run very fast, with a very low memory footprint, while achieving very good prediction accuracy (cf this blogpost).
This library offers an interface with snips-nlu-rs, its Rust equivalent for inference only. It allows to persist the NLU pipeline trained with the python code, and load it with the rust code to perform inference. This offers a great portability.

Anyone who agrees with this pull request could vote for it by adding a 👍 to it, and usually, the maintainer will merge it when votes reach 20.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/vinta/awesome-python/pull/1111 **Author:** [@adrienball](https://github.com/adrienball) **Created:** 8/17/2018 **Status:** ❌ Closed **Base:** `master` ← **Head:** `patch-1` --- ### 📝 Commits (2) - [`4111e79`](https://github.com/vinta/awesome-python/commit/4111e79e9b02aae3664097bef8cd58f92b68d67e) Add Snips NLU library in Natural Language Processing section - [`ca31408`](https://github.com/vinta/awesome-python/commit/ca3140828f319b53ce9479e36681f5c6435b6ba5) Merge branch 'master' into patch-1 ### 📊 Changes **1 file changed** (+1 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) </details> ### 📄 Description ## What is this Python project? Snips NLU is a natural language understanding library dedicated to *Intent Parsing* and *Entity Extraction*. It is based on machine learning and makes use of [Logistic Regression](https://en.wikipedia.org/wiki/Logistic_regression) and [Conditional Random Fields](https://en.wikipedia.org/wiki/Conditional_random_field). Consider the following sentence: ``` "What will be the weather in paris at 9pm?" ``` After proper training, the Snips NLU library allows 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" } ] } ``` ## What's the difference between this Python project and similar ones? - The purpose of Snips NLU is more high-level than libraries such as spaCy or NLTK and can be directly used to build chatbots for instance. - Snips NLU has been designed to run very fast, with a very low memory footprint, while achieving very good prediction accuracy (cf [this blogpost](https://medium.com/snips-ai/an-introduction-to-snips-nlu-the-open-source-library-behind-snips-embedded-voice-platform-b12b1a60a41a)). - This library offers an interface with [`snips-nlu-rs`](https://github.com/snipsco/snips-nlu-rs), its Rust equivalent for inference only. It allows to persist the NLU pipeline trained with the python code, and load it with the rust code to perform inference. This offers a great portability. ---------- Anyone who agrees with this pull request could vote for it by adding a :+1: to it, and usually, the maintainer will merge it when votes reach **20**. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2025-11-06 13:07:01 -06:00

GiteaMirror closed this issue

2025-11-06 13:07:01 -06:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/awesome-python#995