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
470
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
snlp2025_prevent_llm_spikes
takase
0
410
[IBIS 2025] 深層基盤モデルのための強化学習驚きから理論にもとづく納得へ
akifumi_wachi
13
6.9k
投資戦略202508
pw
0
570
病院向け生成AIプロダクト開発の実践と課題
hagino3000
0
380
MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation
satai
4
430
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
240
【輪講資料】Moshi: a speech-text foundation model for real-time dialogue
hpprc
3
800
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
1.1k
20250725-bet-ai-day
cipepser
3
530
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
5.1k
[RSJ25] Enhancing VLA Performance in Understanding and Executing Free-form Instructions via Visual Prompt-based Paraphrasing
keio_smilab
PRO
0
170
国際論文を出そう!ICRA / IROS / RA-L への論文投稿の心構えとノウハウ / RSJ2025 Luncheon Seminar
koide3
10
6.1k
Featured
See All Featured
The Cost Of JavaScript in 2023
addyosmani
55
9.3k
Statistics for Hackers
jakevdp
799
230k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
196
67k
GitHub's CSS Performance
jonrohan
1032
470k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3k
Making Projects Easy
brettharned
120
6.5k
Raft: Consensus for Rubyists
vanstee
140
7.2k
Principles of Awesome APIs and How to Build Them.
keavy
127
17k
Code Reviewing Like a Champion
maltzj
527
40k
Build The Right Thing And Hit Your Dates
maggiecrowley
38
2.9k
Optimising Largest Contentful Paint
csswizardry
37
3.5k
Building Applications with DynamoDB
mza
96
6.8k
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