Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
The state of NLP in production 🥽
Search
Abdur-Rahmaan Janhangeer
August 27, 2023
Programming
0
71
The state of NLP in production 🥽
NLP in production vs real life
Abdur-Rahmaan Janhangeer
August 27, 2023
Tweet
Share
More Decks by Abdur-Rahmaan Janhangeer
See All by Abdur-Rahmaan Janhangeer
Extending Flask using the Flask Plugins API
osdotsystem
0
23
PEPs that hit the front page
osdotsystem
0
33
libSQL: Taking Sqlite To The Moon
osdotsystem
0
110
Boosting Python With Rust 🚀
osdotsystem
0
130
Flet: Flutter in Python
osdotsystem
0
260
SQLite Internals: How The World's Most Used Database Works
osdotsystem
2
3.5k
Fast Flask Dev For Big Codebases
osdotsystem
0
150
Python Bytecode or How Python Operates
osdotsystem
0
220
How To OpenSource
osdotsystem
0
120
Other Decks in Programming
See All in Programming
デザインシステムとコンポーネント指向によるフロントエンド開発プロセスの革新 / Innovation in Frontend Development Processes through Design Systems and Component-Oriented Architecture
nrslib
7
5k
Swiftで高速フーリエ変換してオーディオビジュアライザーを作る / iOSDC Japan 2024 Day1 Track D
kyome22
2
460
Some more adventure of Happy Eyeballs
coe401_
2
150
ECMAScript仕様を読むのに必要な知識 - ダイジェスト版
syumai
4
2.5k
Rubyのobject_id
qnighy
6
1.3k
iOSDC 2024
auramagi
3
590
BasicBasic認証
sadnessojisan
5
2.5k
私のEbitengineの第一歩
qt_luigi
0
410
LR で JSON パーサーを作る / Coding LR JSON Parser
junk0612
2
170
最高の構文木の設計 2024年版
yui_knk
7
2.3k
ECMAScript、Web標準の型はどう管理されているか / How ECMAScript and Web standards types are maintained
petamoriken
3
360
connect-go で面倒くささと戦う / 2024-08-27 #newmo_layerx_go
izumin5210
2
580
Featured
See All Featured
Design by the Numbers
sachag
277
19k
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.4k
Bash Introduction
62gerente
608
210k
The Art of Programming - Codeland 2020
erikaheidi
48
13k
Faster Mobile Websites
deanohume
304
30k
RailsConf 2023
tenderlove
26
790
Infographics Made Easy
chrislema
239
18k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
22
580
Fireside Chat
paigeccino
31
2.9k
Agile that works and the tools we love
rasmusluckow
327
20k
Into the Great Unknown - MozCon
thekraken
28
1.4k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
190
16k
Transcript
The state of NLP in production
None
Python Mauritius Usergroup site fb linkedin mailing list 3
url pymug.com site 4
About me compileralchemy.com 5
slides 6
The state of NLP in production 7
Hardest part of a real-world project 8
? 9
Is it cooking up an awesome model? 10
No, the world is more complex than this 11
Elements of an NLP project 12
NLP project gather data clean store train use model retrain
model 13
gather data 14
Toy project use curated data set quick extraction 15
Real project a lot of data needed data corresponds to
business case. data probably does not exist speed of data gathering find ingenious / better ways of getting data automate collection 16
clean/preprocess data 17
Toy project use an existing parser / curator e.g. NLTK
existing options 18
Real project use a parser intended for it, several custom
steps parallel processing of data 19
store data 20
Toy project laptop 21
Real project cloud database hot / cold data TTL 22
training 23
Toy project use laptop / external GPU 24
Real project on cloud training on cloud knowledge cross-cloud skills
fault tolerance 25
use model 26
Toy project local website / code 27
Real project continuation of pipeline web service architecture devops /
deploy 28
retraining 29
Toy project euhh this even exists???? 30
Real project learn cloud offerings for continuous learning ways to
retrain / fine tune 31
It's more than serving a model 32
Operation model 33
[ pipeline ] data collection --- process --- train -<-
| | --------------------------- model ^ | | | | --->--- V web service [pod] [pod] --- happy user | -> users service [pod] [pod] | -> db service [pod] 34
skills chart 35
skills --------------- --------------- | | | | | backend |
| devops | | | | | --------------- --------------- --------------- --------------- | | | | | backend | | data eng | | | | | --------------- --------------- 36
skills --------------- --------------- | | | | | backend |
| devops | | | | | --------------- --------------- web service deploy --------------- --------------- | | | | | ml | | data eng | | | | | --------------- --------------- models pipelining 37
code blueprint [ architecture repos ] [ pipeline repos ]
[ ml repos ] [ backend repos ] 38
Tools 39
Pandas Good queries Much resources Read SQL 40
Dask Good for it's purpose: Parallelize tasks Poor docs 41
Polars Awesome parallelizations Great docs 42
NLTK use spacy if possible 43
Notebooks great for cloud used in production on the cloud
44
Advice to research / scientists folks keep everything clean people
will come after you always in hurry / messy / i'll clean it later mood good practices? is this phrase in the korean dictionary? 45
General advices have great docs good onboarding have great standards
46
Keep learning! 47