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
論文紹介: Neural Relation Extraction for Knowledge ...
Search
Koji Matsuda
September 27, 2019
Research
0
430
論文紹介: Neural Relation Extraction for Knowledge Base Enrichment (ACL2019)
Koji Matsuda
September 27, 2019
Tweet
Share
More Decks by Koji Matsuda
See All by Koji Matsuda
Editing Factual Knowledge in Language Models (EMNLP 2021)
conditional
0
360
SHINRA2020-JP リーダーボードのご案内
conditional
0
190
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
330
Other Decks in Research
See All in Research
When Submarine Cables Go Dark: Examining the Web Services Resilience Amid Global Internet Disruptions
irvin
0
230
Looking for Escorts in Sydney?
lunsophia
1
120
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
7
2.9k
公立高校入試等に対する受入保留アルゴリズム(DA)導入の提言
shunyanoda
0
6k
Transparency to sustain open science infrastructure - Printemps Couperin
mlarrieu
1
190
Collaborative Development of Foundation Models at Japanese Academia
odashi
2
560
ASSADS:ASMR動画に合わせて撫でられる感覚を提示するシステムの開発と評価 / ec75-shimizu
yumulab
1
400
rtrec@dbem6
myui
6
880
近似動的計画入門
mickey_kubo
4
980
EarthMarker: A Visual Prompting Multimodal Large Language Model for Remote Sensing
satai
3
350
SSII2025 [TS3] 医工連携における画像情報学研究
ssii
PRO
2
1.2k
電力システム最適化入門
mickey_kubo
1
700
Featured
See All Featured
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
Reflections from 52 weeks, 52 projects
jeffersonlam
351
20k
Adopting Sorbet at Scale
ufuk
77
9.5k
Faster Mobile Websites
deanohume
307
31k
It's Worth the Effort
3n
185
28k
Facilitating Awesome Meetings
lara
54
6.4k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
107
19k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
161
15k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
Mobile First: as difficult as doing things right
swwweet
223
9.7k
Transcript
Neural Relation Extraction for Knowledge Base Enrichment Bayu Distiawan Trisedya,
Gerhard Weikum, Jianzhong Qi, Rui Zhang ACL 2019 հऀ: দాߞ࢙ (ཧݚAIP/౦େ) ୈ11ճ࠷ઌ NLP ษڧձ (γϣʔτ) εϥΠυதͷਤදಛʹऍ͕ͳ͍ݶΓจ͔ΒͷҾ༻Ͱ͢ 1 YAGOͷ։ൃऀ
• MEKG'"$) >9 GD – KG Enrichment
• =1 (: Seq2Seq 2 • @C – ?F#-*>986 IB!0' '34L< – K7IB JA;",+&, n-gram Attention – ?F#-*5).+/*/ % Precision:H 2
: (Wikidata) 3
KG Enrichment Information Extraction ΤϯςΟςΟͱؔΛ WikidataͷIDʹਖ਼نԽ͍ͨ͠ NED => ؔநग़
ͳύΠϓϥΠϯ͕ϕʔεϥΠϯ 4
: New York University
is a private university in Manhattan. Encoder (LSTM) N-gram Attention Decoder (LSTM) Triple Classifier <Q49210 P31 Q902104> <Q49210 P131 Q11299> ᶄ ᶅ Joint Embedding ᶃ ೖྗจ ग़ྗ 5 ೖग़ྗͷϖΞ Distant SupervisionͰੜ
: KG • TransE +
Skip-gram – Anchor Context Model [Yamada 16] 6 New York University is a private university in Manhattan Q49210 is a Q902104 in Q11299 J = +
: N-gram Attention • Entity-mention
– ”New York University” • “New York”, “York University” … 7 3-gram·Ͱͷn-gram
: Triple Classifier • 5<"+(/ 5< (-% –
9: <New York University, capital of, Manhattan> • TransE '- 04&,)-= 7@23$#*!&- 6;.> – (h + r – t) – .>: Negative Sample 81? 8
• ;87/! Distant Supervision – Co-reference – -4#(6#'
3 2 • ;8!* ) ., &!'1 – <New York University, Q49210>$ ;8!9 • ) .,0: "% + (533.5) 9
10 ύΠϓϥΠ ϯμϝ N-gram Attention ޮՌൃش ClassifierͰ Precisionվળ
New York University is a private university in Manhattan.
Encoder (LSTM) N-gram Attention Decoder (LSTM) Triple Classifier <Q49210 P31 Q902104> <Q49210 P131 Q11299> ᶄ ᶅ Joint Embedding ᶃ ೖྗจ ग़ྗ 11 ೖग़ྗͷϖΞ Distant SupervisionͰੜ
• ! • – DS
train/test test 12