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
320
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
290
SHINRA2020-JP リーダーボードのご案内
conditional
0
130
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
Discovering Universal Geometry in Embeddings with ICA
momoseoyama
1
350
VAR モデルによる OSS プロジェクト同士が生存性に与える 影響の分析
noppoman
0
130
継続的な研究費獲得のための考え方
moda0
0
200
MegaParticles: GPUを利用したStein Particle Filterによる点群6自由度姿勢推定
koide3
1
530
音声処理ツールキットESPnetの現在と未来
kanbayashi1125
2
540
DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials
tsurubee
0
370
サウナでのプロジェクションマッピングの可能性の検討 / EC71koizumi
yumulab
0
170
ゼロからわかるリザバーコンピューティング
kurotaky
1
300
SSII2023 医療支援における画像処理研究の動向と展望
moda0
0
110
HP (Hitto Point: 筆頭ポイント)
tanichu
0
720
Gmail の「メール送信者のガイドライン」強化から 1 ヵ月、今後予想されるメールセキュリティの変化とは
hirachan
1
240
言語間転移学習で大規模言語モデルを賢くする
ikuyamada
6
3.3k
Featured
See All Featured
The Cult of Friendly URLs
andyhume
74
5.7k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
40
4.4k
Ruby is Unlike a Banana
tanoku
96
10k
Building Adaptive Systems
keathley
31
1.9k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
659
120k
For a Future-Friendly Web
brad_frost
172
9k
How GitHub (no longer) Works
holman
304
140k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
60
14k
Java REST API Framework Comparison - PWX 2021
mraible
PRO
18
6.9k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
25
2.3k
Mobile First: as difficult as doing things right
swwweet
216
8.6k
The MySQL Ecosystem @ GitHub 2015
samlambert
243
12k
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