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
0
480
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
390
SHINRA2020-JP リーダーボードのご案内
conditional
0
210
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
360
Other Decks in Research
See All in Research
離散凸解析に基づく予測付き離散最適化手法 (IBIS '25)
taihei_oki
PRO
1
670
一般道の交通量減少と速度低下についての全国分析と熊本市におけるケーススタディ(20251122 土木計画学研究発表会)
trafficbrain
0
140
ペットのかわいい瞬間を撮影する オートシャッターAIアプリへの スマートラベリングの適用
mssmkmr
0
200
湯村研究室の紹介2025 / yumulab2025
yumulab
0
290
Pythonでジオを使い倒そう! 〜それとFOSS4G Hiroshima 2026のご紹介を少し〜
wata909
0
1.3k
LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
satai
3
410
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
160
学習型データ構造:機械学習を内包する新しいデータ構造の設計と解析
matsui_528
6
2.9k
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
760
都市交通マスタープランとその後への期待@熊本商工会議所・熊本経済同友会
trafficbrain
0
110
生成AI による論文執筆サポート・ワークショップ 論文執筆・推敲編 / Generative AI-Assisted Paper Writing Support Workshop: Drafting and Revision Edition
ks91
PRO
0
110
AIスパコン「さくらONE」のLLM学習ベンチマークによる性能評価 / SAKURAONE LLM Training Benchmarking
yuukit
2
950
Featured
See All Featured
The Curious Case for Waylosing
cassininazir
0
230
The SEO identity crisis: Don't let AI make you average
varn
0
57
From π to Pie charts
rasagy
0
120
Balancing Empowerment & Direction
lara
5
860
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
87
Designing for humans not robots
tammielis
254
26k
Code Reviewing Like a Champion
maltzj
527
40k
How Software Deployment tools have changed in the past 20 years
geshan
0
31k
Heart Work Chapter 1 - Part 1
lfama
PRO
5
35k
Navigating Algorithm Shifts & AI Overviews - #SMXNext
aleyda
0
1.1k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
1
110
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