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
130
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
Building AI Agents with Python: A Deep Dive
osdotsystem
0
20
Extending Flask using the Flask Plugins API
osdotsystem
0
100
PEPs that hit the front page
osdotsystem
0
87
libSQL: Taking Sqlite To The Moon
osdotsystem
0
200
Boosting Python With Rust 🚀
osdotsystem
0
190
Flet: Flutter in Python
osdotsystem
0
420
SQLite Internals: How The World's Most Used Database Works
osdotsystem
2
3.7k
Fast Flask Dev For Big Codebases
osdotsystem
0
220
Python Bytecode or How Python Operates
osdotsystem
0
300
Other Decks in Programming
See All in Programming
「App Intent」よくわからんけどすごい!
rinngo0302
1
100
Rails Frontend Evolution: It Was a Setup All Along
skryukov
0
260
Porting a visionOS App to Android XR
akkeylab
0
670
猫と暮らす Google Nest Cam生活🐈 / WebRTC with Google Nest Cam
yutailang0119
0
170
『自分のデータだけ見せたい!』を叶える──Laravel × Casbin で複雑権限をスッキリ解きほぐす 25 分
akitotsukahara
2
660
Git Sync を超える!OSS で実現する CDK Pull 型デプロイ / Deploying CDK with PipeCD in Pull-style
tkikuc
4
320
チームで開発し事業を加速するための"良い"設計の考え方 @ サポーターズCoLab 2025-07-08
agatan
1
460
新メンバーも今日から大活躍!SREが支えるスケールし続ける組織のオンボーディング
honmarkhunt
5
8.5k
Advanced Micro Frontends: Multi Version/ Framework Scenarios @WAD 2025, Berlin
manfredsteyer
PRO
0
380
AIと”コードの評価関数”を共有する / Share the "code evaluation function" with AI
euglena1215
1
180
ソフトウェア品質を数字で捉える技術。事業成長を支えるシステム品質の マネジメント
takuya542
2
15k
TypeScriptでDXを上げろ! Hono編
yusukebe
3
730
Featured
See All Featured
Mobile First: as difficult as doing things right
swwweet
223
9.7k
Speed Design
sergeychernyshev
32
1k
Navigating Team Friction
lara
187
15k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
22k
How to train your dragon (web standard)
notwaldorf
96
6.1k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
251
21k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
18
980
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
229
22k
GraphQLとの向き合い方2022年版
quramy
49
14k
The Pragmatic Product Professional
lauravandoore
35
6.7k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
Docker and Python
trallard
45
3.5k
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