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
A Natural Language Pipeline
Search
ddqz
July 06, 2019
Technology
0
420
A Natural Language Pipeline
Presentation from the spaCy IRL 2019 conference.
ddqz
July 06, 2019
Tweet
Share
Other Decks in Technology
See All in Technology
今さら聞けないDocker入門 〜 Dockerfileのベストプラクティス編
devops_vtj
21
6.3k
ルーターでプレゼンする
puhitaku
1
3.4k
個人のAWSアカウントをマルチ運用してみた
miura55
2
250
成長をサポートするピープルマネジメントのやり方
sioncojp
9
1.4k
プロンプトエンジニアリングでがんばらない-Agentic Workflow へ-近藤憲児
kenjikondobai
6
1.3k
Documentação de Produtos: Artefatos essenciais na prática
rigolon
1
220
IaCジェネレーターとBedrockで詳細設計書を生成してみた
tsukasa_ishimaru
4
950
同じ様なUIをiOS/Android間で合わせるヒントNo.2
fumiyasac0921
1
110
Cypress or Playwright?
rainerhahnekamp
0
180
モーダル間の変換後の一致性とジャンル表を用いた解釈可能性の考察 ~Text-to-MusicとText-To-ImageかつImage-to-Musicを例に~
otanet
0
320
LLM開発・活用の舞台裏@2024.04.25
yushin_n
3
1.4k
コードファーストの考え方。 Amplify Gen2から学ぶAWS次世代のWeb開発体験
yoshiitaka
2
530
Featured
See All Featured
A Modern Web Designer's Workflow
chriscoyier
689
190k
The Art of Programming - Codeland 2020
erikaheidi
43
12k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
242
1.2M
Dealing with People You Can't Stand - Big Design 2015
cassininazir
358
22k
Designing for Performance
lara
601
67k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
155
14k
Making Projects Easy
brettharned
109
5.5k
Adopting Sorbet at Scale
ufuk
69
8.6k
Writing Fast Ruby
sferik
622
60k
VelocityConf: Rendering Performance Case Studies
addyosmani
321
23k
Statistics for Hackers
jakevdp
790
220k
Web development in the modern age
philhawksworth
203
10k
Transcript
A Natural Language Pipeline
More Input
Knowledge” “A compendium of human...
Library
Physical archives became digital records, encoded with metadata
The internet promised rich dynamic experiences
The internet promised rich dynamic experiences but served us banner
ads
Advertising has and continues to fuel a substantial portion of
the innovation on the internet
What would The Economist look like if it were founded
in 2012?
User
First
Experience
“There’s a reason that tech companies are topping the lists
of most valuable companies and brands. Every company is a tech company.” Maggie Chan Jones
Every story, at its core, is a business story
Language
None
None
Stage -> Stenographer -> Editors -> spaCy -> Data Store
<-> Backend <- Slack <- Users Proto-Pipeline
Over eight hours we created data from the content of
the event, building the model in real-time
The model evolved over time
This was the experiment that would evolve into SiO 2
Silicon, a key element in everything from glass to microchips,
is at the core of global business
Oxygen, the journalistic voice Quartz breathes into the global business
news cycle
Entities are linguistic anchors, defined by context and around which
context can be inferred
Standard Entities PERSON FACILITY ORG PRODUCT GPE EVENT... Additional Entities
TECHNOLOGY PROCESS NATURE MEDIA CONSTRUCT
70K articles 1.4M blocks of text 85K labeled sentences
Entities
This spaCy model made rich analysis for any given text
easy to do on the fly
Stored analysis of a large corpus is a vital resource
The language graph...
Graph
The language graph is a mutable map of the language
model
Any new content is analyzed and then mapped onto the
language graph
Changes made to the graph can then be incorporated into
the next model iteration
The language graph becomes a primary resource for extracting training
data
Snapshots of time can be extracted from the language graph
Context can be derived by looking at the relationships in
the language graph
Elon Musk
Jeff Bezos
Mark Zuckerberg
Context
SiO 2 is a living Natural Language Pipeline of networked
algorithms trained on the corpus of Quartz to understand the linguistic patterns of global business news
The Pipeline(s) Quartz Corpus -> Training Sentences -> spaCy Content
-> spaCy -> Language Graph Language Graph -> Training Data -> Statistical Models / Classifiers Language Graph -> Training Sentences -> spaCy Unseen Content -> spaCy -> Pre-Processed Text / Vectors -> Statistical Models / Classifiers
Thank you