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
重要だけど測れていないもの:高齢者ケアの見えない課題
theoriatec2024
0
460
Harness Engineering and Al Agent
kzinmr
3
1.9k
Sleuthcon Keynote - How Cybercriminals (ab)use AI
fr0gger
0
290
CVPR2026論文紹介_VLMにとって良いvision encoderとは何か?Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
kobayashi31
1
190
2026年 オープンキャンパス 研究室紹介
junkurihara
0
110
Visual SLAM未来予測 / Future Prediction in Visual SLAM
koide3
1
870
PHTalks Bengaluru - SSRF When All Else Fails
dk999
0
1k
シングルチャネルマルチトーカー音声認識の進展
ryomasumura
0
210
言語モデルから言語について語る際に押さえておきたいこと
eumesy
PRO
7
2.5k
LLM Compute Infrastructure Overview
karakurist
2
1.6k
HackSick vol.7 LT資料【LLMアーキテクチャ入門・事前学習時の躓き所解説】 スパースなAttention・状態空間モデル
rikkabotan7
0
150
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
200
Featured
See All Featured
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
10
1.3k
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
4 Signs Your Business is Dying
shpigford
187
23k
Building Applications with DynamoDB
mza
96
7.2k
Technical Leadership for Architectural Decision Making
baasie
3
480
Optimising Largest Contentful Paint
csswizardry
37
3.9k
Imperfection Machines: The Place of Print at Facebook
scottboms
270
14k
Writing Fast Ruby
sferik
630
63k
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
63
45k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
inesmontani
PRO
3
2.3k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.6k
Leo the Paperboy
mayatellez
8
2.1k
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