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
51
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
PEPs that hit the front page
osdotsystem
0
10
libSQL: Taking Sqlite To The Moon
osdotsystem
0
79
Boosting Python With Rust 🚀
osdotsystem
0
110
Flet: Flutter in Python
osdotsystem
0
160
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
200
How To OpenSource
osdotsystem
0
110
Python's Bytecode
osdotsystem
0
110
Other Decks in Programming
See All in Programming
From Spring Boot 2 to Spring Boot 3 with Java 21 and Jakarta EE
ivargrimstad
0
120
CA.swift19 恋するAIアプリ開発の裏側
oskmr
0
360
障害対応を起点としたもっといい開発と運用のサイクル作りのためにできること / Hatena Enginner Seminar #29
polamjag
0
220
Scalable Customer Journey Orchestration (CJO)
lewuathe
0
340
try! Swift Tokyo 初参加報告LT
hinakko2
0
220
検証も兼ねて個人開発でHonoとかと向き合った話
hanetsuki
1
1.1k
Ruby GitHub Packages
bkuhlmann
0
630
AWS CDKコントリビュートTIPS / aws-cdk-contribution-tips
gotok365
2
200
PHPはいつから死んでいるかの調査
chiroruxx
1
400
SIMD Parallel Programming with the Vector API
josepaumard
0
180
VS Code をプロダクトにどう取り込むか
onomax
1
370
AWS Application Composerで始める、 サーバーレスなデータ基盤構築 / 20240406-jawsug-hokuriku-shinkansen
kasacchiful
1
260
Featured
See All Featured
Docker and Python
trallard
34
2.7k
Agile that works and the tools we love
rasmusluckow
325
20k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
244
20k
Making the Leap to Tech Lead
cromwellryan
124
8.5k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
17
1.4k
Typedesign – Prime Four
hannesfritz
36
2.1k
Git: the NoSQL Database
bkeepers
PRO
422
63k
Fireside Chat
paigeccino
21
2.6k
The Power of CSS Pseudo Elements
geoffreycrofte
60
5k
Building an army of robots
kneath
300
41k
What the flash - Photography Introduction
edds
64
11k
Writing Fast Ruby
sferik
621
60k
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