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
460
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
380
SHINRA2020-JP リーダーボードのご案内
conditional
0
200
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
350
Other Decks in Research
See All in Research
スキマバイトサービスにおける現場起点でのデザインアプローチ
yoshioshingyouji
0
250
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
63
33k
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
230
RHO-1: Not All Tokens Are What You Need
sansan_randd
1
200
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
1.1k
説明可能な機械学習と数理最適化
kelicht
0
330
論文紹介: ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
hisaokatsumi
0
110
Minimax and Bayes Optimal Best-arm Identification: Adaptive Experimental Design for Treatment Choice
masakat0
0
180
さまざまなAgent FrameworkとAIエージェントの評価
ymd65536
1
180
アニメにおける宇宙猫ミームとその表現
yttrium173340
0
110
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
2
580
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
520
Featured
See All Featured
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
2.9k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
127
54k
Fireside Chat
paigeccino
41
3.7k
Agile that works and the tools we love
rasmusluckow
331
21k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Building a Scalable Design System with Sketch
lauravandoore
463
33k
Imperfection Machines: The Place of Print at Facebook
scottboms
269
13k
The Language of Interfaces
destraynor
162
25k
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.3k
Designing for Performance
lara
610
69k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
54k
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