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 Base Enrichment (ACL2019)
Search
Koji Matsuda
September 27, 2019
Research
0
340
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
300
SHINRA2020-JP リーダーボードのご案内
conditional
0
140
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
280
Other Decks in Research
See All in Research
動物倫理学ことはじめ:人間以外の動物との倫理的な付き合い方を考える
takeshit_m
0
350
第60回名古屋CV・PRML勉強会:CVPR2024論文紹介(AM-RADIO)
naok615
0
120
自動運転・AIシステムの問題を賢く探す・賢く直す / Smart Search & Repair Techniques for Automated Driving Systems and AI Systems
ishikawafyu
0
130
独立成分分析を用いた埋め込み表現の視覚的な理解
momoseoyama
3
770
AIが非ヒト動物に与える有益・有害な影響の検討
takeshit_m
0
290
インタビューだけじゃない!ユーザーに共感しユーザーの目👀を手に入れるためのインプット
moco1013
0
430
初めての研究発表を成功させよう! スライド作成の基本
ayaco0
10
4.1k
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction(日本語版)
aiueola
0
120
研究効率化Tips_2024 / Research Efficiency Tips 2024
ryo_nakamura
5
4.1k
ヘルプデスクの事例で学ぶAIエージェント
masatoto
11
4.5k
SSII2024 [OS1] 画像認識におけるモデル・データの共進化
ssii
PRO
0
380
1on1ガイドへの想い(chachaki編)
chachakix
0
150
Featured
See All Featured
Building an army of robots
kneath
301
42k
Design by the Numbers
sachag
277
18k
Code Review Best Practice
trishagee
58
16k
A better future with KSS
kneath
231
17k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
149
45k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
26
1.8k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
224
21k
[RailsConf 2023] Rails as a piece of cake
palkan
35
4.4k
10 Git Anti Patterns You Should be Aware of
lemiorhan
652
58k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
189
16k
Build your cross-platform service in a week with App Engine
jlugia
227
17k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
12
3.8k
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