Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Speaker Deck
PRO
Sign in
Sign up for free
A Natural Language Pipeline
ddqz
July 06, 2019
Technology
0
320
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
Hatena Engineer Seminar #23 「チームとプロダクトを育てる Mackerel 開発合宿」
arthur1
0
190
03_ユーザビリティテスト
kouzoukaikaku
0
290
OPENLOGI Company Profile
hr01
0
12k
Multi-Cloud Gatewayでデータを統治せよ!/ Data Federation with MCG
tutsunom
1
210
WebLogic Server for OCI 概要
oracle4engineer
PRO
3
870
ユーザーテストガイドライン VERSION 2.0
kouzoukaikaku
0
1.1k
書籍を書きました。 そう、VS Codeで。
takumanakagame
4
3.6k
データ分析基盤の要件分析の話(202201_JEDAI)
yabooun
0
240
証明書って何だっけ? 〜AWSの中間CA移行に備える〜
minorun365
3
2.1k
地方自治体業務あるある ーアナログ最適化編-
y150saya
1
240
Kaggleシミュレーションコンペの動向
nagiss
0
260
Stripe / Okta Customer Identity Cloud(旧Auth0) の採用に至った理由 〜モリサワの SaaS 戦略〜
tomuro
0
120
Featured
See All Featured
Music & Morning Musume
bryan
37
4.6k
Atom: Resistance is Futile
akmur
256
24k
Web Components: a chance to create the future
zenorocha
304
40k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
6
840
Typedesign – Prime Four
hannesfritz
34
1.5k
GraphQLの誤解/rethinking-graphql
sonatard
39
7.8k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
10
1.3k
Testing 201, or: Great Expectations
jmmastey
25
5.7k
BBQ
matthewcrist
75
8.1k
The Invisible Side of Design
smashingmag
292
48k
The Web Native Designer (August 2011)
paulrobertlloyd
76
2.2k
Keith and Marios Guide to Fast Websites
keithpitt
407
21k
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