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
Cross-Media Information Spaces and Architectures
signer
PRO
0
230
Delta Airlines® Customer Care in the U.S.: How to Reach Them Now
bookingcomcustomersupportusa
PRO
0
100
Mathematics in the Age of AI and the 4 Generation University
hachama
0
170
【緊急警告】日本の未来設計図 ~沈没か、再生か。国民と断行するラストチャンス~
yuutakasan
0
140
時系列データに対する解釈可能な 決定木クラスタリング
mickey_kubo
2
760
SSII2025 [TS3] 医工連携における画像情報学研究
ssii
PRO
2
1.2k
2025年度 生成AIの使い方/接し方
hkefka385
1
720
Looking for Escorts in Sydney?
lunsophia
1
120
Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction
satai
3
220
利用シーンを意識した推薦システム〜SpotifyとAmazonの事例から〜
kuri8ive
1
210
集合間Bregmanダイバージェンスと置換不変NNによるその学習
wasyro
0
110
近似動的計画入門
mickey_kubo
4
980
Featured
See All Featured
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
130
19k
What's in a price? How to price your products and services
michaelherold
246
12k
Raft: Consensus for Rubyists
vanstee
140
7k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
30
2.1k
Mobile First: as difficult as doing things right
swwweet
223
9.7k
Intergalactic Javascript Robots from Outer Space
tanoku
271
27k
Embracing the Ebb and Flow
colly
86
4.7k
Art, The Web, and Tiny UX
lynnandtonic
299
21k
YesSQL, Process and Tooling at Scale
rocio
173
14k
The Straight Up "How To Draw Better" Workshop
denniskardys
235
140k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
2.9k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
31
1.3k
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