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
420
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
350
SHINRA2020-JP リーダーボードのご案内
conditional
0
170
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
310
Other Decks in Research
See All in Research
VAGeo: View-specific Attention for Cross-View Object Geo-Localization
satai
3
180
LLM 시대의 Compliance: Safety & Security
huffon
0
630
大規模言語モデルを用いたニュースデータのセンチメント判定モデルの開発および実体経済センチメントインデックスの構成
nomamist
1
160
ドローンやICTを活用した持続可能なまちづくりに関する研究
nro2daisuke
0
200
EarthMarker: A Visual Prompting Multimodal Large Language Model for Remote Sensing
satai
3
130
インドネシアのQA事情を紹介するの
yujijs
0
180
Satellite Sunroof: High-res Digital Surface Models and Roof Segmentation for Global Solar Mapping
satai
3
270
DeepSeek-R1の論文から読み解く背景技術
personabb
3
530
言語モデルによるAI創薬の進展 / Advancements in AI-Driven Drug Discovery Using Language Models
tsurubee
2
290
Optimal and Diffusion Transports in Machine Learning
gpeyre
0
1.5k
NLP2025参加報告会 LT資料
hargon24
1
250
Individual tree crown delineation in high resolution aerial RGB imagery using StarDist-based model
satai
3
180
Featured
See All Featured
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
4
510
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
Docker and Python
trallard
44
3.3k
How STYLIGHT went responsive
nonsquared
99
5.5k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
Building Applications with DynamoDB
mza
94
6.3k
Speed Design
sergeychernyshev
28
880
Rails Girls Zürich Keynote
gr2m
94
13k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
33
2.2k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
29
2k
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