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
380
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
320
SHINRA2020-JP リーダーボードのご案内
conditional
0
150
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
290
Other Decks in Research
See All in Research
いしかわ暮らしセミナー~移住にまつわるお金の話~
matyuda
0
150
言語と数理の交差点:テキストの埋め込みと構造のモデル化 (IBIS 2024 チュートリアル)
yukiar
3
730
20240918 交通くまもとーく 未来の鉄道網編(こねくま)
trafficbrain
0
230
KDD論文読み会2024: False Positive in A/B Tests
ryotoitoi
0
200
SNLP2024:Planning Like Human: A Dual-process Framework for Dialogue Planning
yukizenimoto
1
330
FOSS4G 山陰 Meetup 2024@砂丘 はじめの挨拶
wata909
1
110
Weekly AI Agents News!
masatoto
25
24k
湯村研究室の紹介2024 / yumulab2024
yumulab
0
280
ニューラルネットワークの損失地形
joisino
PRO
35
16k
工学としてのSRE再訪 / Revisiting SRE as Engineering
yuukit
19
11k
ダイナミックプライシング とその実例
skmr2348
3
400
「並列化時代の乱数生成」
abap34
3
820
Featured
See All Featured
We Have a Design System, Now What?
morganepeng
50
7.2k
KATA
mclloyd
29
14k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
26
1.4k
Designing for Performance
lara
604
68k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
28
9.1k
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
StorybookのUI Testing Handbookを読んだ
zakiyama
27
5.3k
Why Our Code Smells
bkeepers
PRO
334
57k
A better future with KSS
kneath
238
17k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
27
4.3k
A designer walks into a library…
pauljervisheath
204
24k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
246
1.3M
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