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
500
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
論文紹介: Neural Relation Extraction for Knowledge Base Enrichment (ACL2019)
Koji Matsuda
September 27, 2019
More Decks by Koji Matsuda
See All by Koji Matsuda
Editing Factual Knowledge in Language Models (EMNLP 2021)
conditional
0
390
SHINRA2020-JP リーダーボードのご案内
conditional
0
230
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
380
Other Decks in Research
See All in Research
HAKARI-Bench - 実運用視点での情報検索モデル評価ベンチマーク
hotchpotch
1
720
J-STAGEの現況と全文XML登載必須化について
xspa2012
0
180
セマンティック通信勉強会 6Gに向けたデバイス間効率的な通信の技術紹介・課題・今後展望
satai
3
310
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
560
2026年度 生成AI を活用した論文執筆ガイド/ワークショップ / 2026 Academic Year Guide to Writing Papers Using Generative AI - Workshop
ks91
PRO
0
220
Cross-Media Human-Information Interaction
signer
PRO
0
210
[最先端NLP勉強会2026] Checklists Are Better Than Reward Models For Aligning Language Models
nzw0301
1
300
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
satai
3
520
MM-OVSeg: Multimodal Optical–SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
satai
3
120
Research Engineerという仕事 / Research Engineering: Bridging Research and Business
chck
1
290
Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
satai
3
120
Source Code Diff Revolution
tsantalis
0
120
Featured
See All Featured
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
400
How to Build an AI Search Optimization Roadmap - Criteria and Steps to Take #SEOIRL
aleyda
1
2.2k
RailsConf 2023
tenderlove
30
1.5k
Learning to Love Humans: Emotional Interface Design
aarron
275
41k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Agile Leadership in an Agile Organization
kimpetersen
PRO
0
220
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
123
22k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
3
1.2k
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
6
1.2k
Between Models and Reality
mayunak
4
440
Building Experiences: Design Systems, User Experience, and Full Site Editing
marktimemedia
0
590
The SEO Collaboration Effect
kristinabergwall1
1
540
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