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
440
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
370
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
340
Other Decks in Research
See All in Research
データxデジタルマップで拓く ミラノ発・地域共創最前線
mapconcierge4agu
0
210
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
120
Language Models Are Implicitly Continuous
eumesy
PRO
0
220
単施設でできる臨床研究の考え方
shuntaros
0
2.7k
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
260
電力システム最適化入門
mickey_kubo
1
910
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
750
RHO-1: Not All Tokens Are What You Need
sansan_randd
1
170
MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation
satai
4
180
生成的推薦の人気バイアスの分析:暗記の観点から / JSAI2025
upura
0
260
大規模な2値整数計画問題に対する 効率的な重み付き局所探索法
mickey_kubo
1
360
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
2.8k
Featured
See All Featured
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
30
9.6k
Stop Working from a Prison Cell
hatefulcrawdad
271
21k
How to train your dragon (web standard)
notwaldorf
96
6.2k
Context Engineering - Making Every Token Count
addyosmani
1
27
Intergalactic Javascript Robots from Outer Space
tanoku
272
27k
A Tale of Four Properties
chriscoyier
160
23k
Why Our Code Smells
bkeepers
PRO
339
57k
The Invisible Side of Design
smashingmag
301
51k
Faster Mobile Websites
deanohume
309
31k
BBQ
matthewcrist
89
9.8k
Six Lessons from altMBA
skipperchong
28
4k
Site-Speed That Sticks
csswizardry
10
810
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