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
400
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
330
SHINRA2020-JP リーダーボードのご案内
conditional
0
160
AI王 〜クイズAI日本一決定戦〜
conditional
0
11k
Training Classifiers with Natural Language Explanations
conditional
0
300
Other Decks in Research
See All in Research
文化が形作る音楽推薦の消費と、その逆
kuri8ive
0
220
Weekly AI Agents News! 9月号 論文のアーカイブ
masatoto
1
170
EBPMにおける生成AI活用について
daimoriwaki
0
250
言語と数理の交差点:テキストの埋め込みと構造のモデル化 (IBIS 2024 チュートリアル)
yukiar
4
1k
データサイエンティストをめぐる環境の違い 2024年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
930
医療支援AI開発における臨床と情報学の連携を円滑に進めるために
moda0
0
140
地理空間情報と自然言語処理:「地球の歩き方旅行記データセット」の高付加価値化を通じて
hiroki13
1
160
「熊本県内バス・電車無料デー」の振り返りとその後の展開@土木計画学SS:成功失敗事例に学ぶ公共交通運賃設定
trafficbrain
0
120
20240918 交通くまもとーく 未来の鉄道網編(こねくま)
trafficbrain
0
400
LLM時代にLabは何をすべきか聞いて回った1年間
hargon24
1
590
Poster: Feasibility of Runtime-Neutral Wasm Instrumentation for Edge-Cloud Workload Handover
chikuwait
0
280
最近のVisual Odometryと Depth Estimation
sgk
1
340
Featured
See All Featured
The Pragmatic Product Professional
lauravandoore
32
6.4k
Mobile First: as difficult as doing things right
swwweet
222
9k
Speed Design
sergeychernyshev
25
740
The Invisible Side of Design
smashingmag
299
50k
KATA
mclloyd
29
14k
A designer walks into a library…
pauljervisheath
205
24k
Statistics for Hackers
jakevdp
797
220k
How to Think Like a Performance Engineer
csswizardry
22
1.3k
Faster Mobile Websites
deanohume
305
30k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
226
22k
Become a Pro
speakerdeck
PRO
26
5.1k
What's in a price? How to price your products and services
michaelherold
244
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