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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Koji Matsuda
September 27, 2019
Research
490
0
Share
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
220
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
370
Other Decks in Research
See All in Research
羽田新ルート運用6年の検証
1manken
0
140
20年前に50代だった人たちの今
hysmrk
0
200
2026 東京科学大 情報通信系 研究室紹介 (大岡山)
icttitech
0
3.3k
LLMアプリケーションの透明性について
fufufukakaka
0
220
台湾モデルに学ぶ詐欺広告対策:市民参加の必要性
dd2030
0
320
それ、チームの改善になってますか?ー「チームとは?」から始めた組織の実験ー
hirakawa51
0
1.1k
コーディングエージェントとABNを再考
hf149
2
590
Can We Teach Logical Reasoning to LLMs? – An Approach Using Synthetic Corpora (AAAI 2026 bridge keynote)
morishtr
1
230
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
140
LLM の Attention 機構まとめ — 数式・計算量・メモリ
puwaer
7
1.8k
正規分布と最適化について
koide3
0
180
Φ-Sat-2のAutoEncoderによる情報圧縮系論文
satai
4
610
Featured
See All Featured
The Spectacular Lies of Maps
axbom
PRO
1
740
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
659
62k
Deep Space Network (abreviated)
tonyrice
0
140
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
49
9.9k
Site-Speed That Sticks
csswizardry
13
1.2k
Color Theory Basics | Prateek | Gurzu
gurzu
0
310
Rebuilding a faster, lazier Slack
samanthasiow
85
9.5k
Large-scale JavaScript Application Architecture
addyosmani
515
110k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.8k
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
1
180
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
2.7k
How to Align SEO within the Product Triangle To Get Buy-In & Support - #RIMC
aleyda
2
1.5k
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