ML Two
Lecture 07
🤗NLP 101: basic tasks with Apple Natural Language Framework😎

Welcome 👩‍🎤🧑‍🎤👨‍🎤

First of all, don't forget to confirm your attendence on Seats App!

Two cover versions of Aphex Twin:
-- Alberto Balsalm but I ran it through Adobe Enhance Speech
-- alberto balsalm chair cover

after today's lecture:
-- Natural Language Processing basic tasks🤖
--- Lemmatisation
--- Named Entity Recognition
--- Part-of-speech tagging
--- Language Identification

NLP:
Natural Language Processing
-- recall data modality?

data modality:
image, text, audio, sensor data, etc.

for example,
object detection is about image data

NLP?
-- look it up on wikipedia
-- "the application of computational techniques to the analysis and synthesis of natural language and speech.""
-- it is an interdisciplinary subfield

Example applications of NLP:
text-to-speech 🗣️
speech-to-text 👂
machine translation 🧠
image captioning 🧑‍🏫
text-to-image generation 🧑‍🎨
etc.

also NLP:
-- Lemmatization
-- Named Entity Recognition
-- Part-of-speech tagging
etc.
❓❓❓

While engaging with languages is very natural to us,
(it is a given, we can use it without fully understanding how our language system works)

NLP can be quite complex and comprises many low-level sub tasks, including:

-- Language identification
-- Lemmatization
-- Named Entity Recognition
-- Part-of-speech tagging
-- Tokenization
etc.

For today's lecture, we will go through each one of these basic tasks with a reference to
🍎 Apple's Natural Language Framework.
- We are not going to look deep into the AI models, instead we just need to know how to use them👐

open an xcode playground, import the framework:

import NaturalLanguage 

import Foundation 

import CoreML

Language identification
--1. what is it about? 🥷
--- try answer by filling out blanks in: Given an input of __, the solution model should produce an output of __
--2. what are the possible use cases? 🧑‍🍳
--3. paste and run the example codes! 🕹️

Named Entity Recognition
--1. what is it about? 🥷
--- try answer by filling out blanks in: Given an input of __, the solution model should produce an output of __
--2. what are the possible use cases? 🧑‍🍳
--3. paste and run the example codes! 🕹️

Jon Rafman made a MV for Kanye and this guy is re-making it using AI tools

Part-of-speech tagging
--1. what is it about? 🥷
--- try answer by filling out blanks in: Given an input of __, the solution model should produce an output of __
--2. what are the possible use cases? 🧑‍🍳
--3. paste and run the example codes! 🕹️

Tokenization
--1. what is it about? 🥷
--- try answer by filling out blanks in: Given an input of __, the solution model should produce an output of __
--2. what are the possible use cases? 🧑‍🍳
--3. paste and run the example codes! 🕹️

🎉

Today we talked about:
-- Lemmatisation
-- Named Entity Recognition
-- Part-of-speech tagging
-- Language Identification
in what these tasks are about and how to use Apple Natural Language Framework for these tasks!

We'll see you next week same time same place! 🫡