Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Facebook Dev-C Meetup| NLP & Architecture
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
_luay
October 27, 2017
Programming
27
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Facebook Dev-C Meetup| NLP & Architecture
_luay
October 27, 2017
Transcript
34 slides
NLP & Architecture Session
Topics Covered • Text Processing & Cleaning. • Sentence Tagging.
• Classification VS Handmade Rules.
Text Processing & Cleaning
Word Tokenization From “my dog hasn't any fleas.” To [
‘my’, ‘dog’, ‘has’, ’n’\t’, ‘any’, ‘fleas’, ‘.’ ]
Word Token vs Word Type • Word Token: Total number
of words in a given sentence, regardless how often they are repeated. • Word Type: Total Number of Distinct words in a sentence.
Example The cushions are new and I can experience the
comfort well. Tokens: 11 Types: 10
Different Tokenizing Algorithms
Stemming Stemmers: Identifying the root word from a token. (e.g
fishing, fished, and fisher) their root is “fish”
Algorithms Porter. (Most commonly used, less aggressive, computational intensive) e.g
“animal -> anim”, “any -> ani“ Lancaster. (Very aggressive) e.g “animal -> anim”, “any -> any”
String Distance • Jaro-Winkler • Levenshtein
Jaro-Winkler Example
Levenshtein Example
Other Techniques • Inflectors. • Phonetics. • N-Grams. • Spellcheck.
• Part of speech tagging. • tf-idf
Sentence Taging
What’s Meant By • I want to read a book.
• I want to eat sandwich. • I want to play football.
What’s Meant By • I want to read that book.
• I read that book. • Did you read that book ? • Can you get me a book to read ? • I don’t want to read that book.
Identify Question Sentences • Do you have my pen? •
How old are you? • What is your name?
Sentences With Numeric Values • I am 23 years old.
• I am twenty three years old. • I am the twenty third.
Sentences With Names • Books by J.K Rowling. • My
name is John.
Identify Sentence Pronouns • Can you help me. • What
are you reading today. • Did you read thinking fast and slow. • Remind me tomorrow at 9 AM.
What’s Meant By • I want to read that book.
• I read that book. • Did you read that book ? • Can you get me a book to read ? • I don’t want to read that book.
Classification & Handmade Rules
Supervised ML • Document. • Fixed Set of classes. •
Training data
Classifier Example
Type of classifiers that are used for NLP • Naive
Bayes. • Logistic regression. • Support-vector machines. • k-Nearest Neighbors.
Handmade Rules
What’s Meant By • I want to read a book.
// Action => recommend Book • I want to eat sandwich. // Action => order sandwich • I want to play football. // Action => find suitable time
What is meant by • I want to read that
book. • I read that book. • Did you read that book ? • Can you get me a book to read ? • I don’t want to read that book.
Tools & Libraries
Examples • wit.ai • api.ai (Dialogflow) • Facbook NLP Engine
• Open source libraries for NLP Classifiers.
Topics Covered • Text Processing & Cleaning. • Sentence Tagging.
• Classification VS Handmade Rules.
Architecture
None
Useful Links • Stanford Natural Language Processing Course: https://goo.gl/FFbyBd •
Andrew NG, Machine Learning Course: https://goo.gl/AXkdyj • Recommended AI Books List: https://goo.gl/Sz9vyX
More Decks by _luay
See All by _luay
The Triumph Of Side Projects - Vol 1👨💻| Intro
_luay
0
40
The Triumph Of Side Projects - Vol 1👨💻| Starting Manual
_luay
0
28
Intel-Meetup.pdf
_luay
0
45
ML-004 From Facebook| Movies Recommendation Case Study 🎬
_luay
0
38
Egyptian Geeks Meetup 🇪🇬| Different Types Of Bean Bags 💼🦄🦓
_luay
0
46
ML-003 From Facebook| Neural Nets In A Nutshell
_luay
0
27
ML-002 From Facebook| AI In A Nutshull 🤖
_luay
0
36
Zewil University Event| The AI Landscape 🤖
_luay
0
53
ML-001 From Facebook| Into The AI Context 🤖
_luay
0
28
Other Decks in Programming
See All in Programming
Debian JP Projectのサーバー構成
uwabami
1
180
AI駆動開発4年目の現在地(『あなたはFDEになるべきか?』イベント資料)
kumaiu
0
700
クラウドエージェントは、 何がそんなに便利なのか / what makes cloud agents so useful
rkaga
5
980
正解の無い問題を 「できるだけ上手く」解く ヒューリスティックで感性を磨こう。〜現実課題をプログラミングで解きあうコミュニティについて〜
allegrogiken
0
110
はじめてのKubernetesコントリビューション
nasa9084
0
320
SODA - FACT BOOK(EN)
sodainc
1
280
Ruby から Emacs を操作したい
phigasui
0
390
仕様駆動開発入門 (何を作るかを先に決めて渡す) | 目指せ Kiro マスター 05
inariku
PRO
3
220
Rails初心者がパスキーを実装してみて大変だったこと
ktombow
0
240
AI時代のFlutter品質設計 — アプリ品質を守るQuality Layers
omatty198
0
390
Scalaの型でマルチテナントの認可を守る
nextbeatdev
0
180
AIが生成したコードは読むべきか?抽象化設計とコードの品質保証 / abstraction-design-and-quality
minodriven
17
9.5k
Featured
See All Featured
The Cult of Friendly URLs
andyhume
79
7.1k
We Are The Robots
honzajavorek
0
460
DevOps and Value Stream Thinking: Enabling flow, efficiency and business value
helenjbeal
2
450
The Limits of Empathy - UXLibs8
cassininazir
2
800
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
1
320
30 Presentation Tips
portentint
PRO
1
480
Abbi's Birthday
coloredviolet
5
11k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.6k
Designing Experiences People Love
moore
143
24k
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
2
540
Technical Leadership for Architectural Decision Making
baasie
4
660
Art, The Web, and Tiny UX
lynnandtonic
304
22k