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
DRETa: Extracting RDF from Wikitables [POSTER]
Search
Emir Muñoz
October 23, 2013
Research
0
57
DRETa: Extracting RDF from Wikitables [POSTER]
DRETa: Extracting RDF from Wikitables
Posters & Demos @ ISWC 2013
Emir Muñoz
October 23, 2013
Tweet
Share
More Decks by Emir Muñoz
See All by Emir Muñoz
Machine Learning Pipelines in Production - ML Galway Meetup
emunoz
0
60
Academic Writing: Hints and Tools
emunoz
0
140
Mining Cardinalities from Knowledge Bases
emunoz
0
170
Using Drug Similarities for Discovery of Possible Adverse Reactions
emunoz
0
110
A Hybrid Method for Rating Prediction Using Linked Data Features and Text Reviews
emunoz
0
170
On Learnability of Cardinality Constraints from RDF Data
emunoz
0
130
Minute Madness ESWC 2016
emunoz
0
100
Tensor Networks---a brief description
emunoz
0
74
A Linked Data-Based Decision Tree Classifier to Review Movies
emunoz
1
170
Other Decks in Research
See All in Research
ECCV2024読み会: Minimalist Vision with Freeform Pixels
hsmtta
1
380
Whoisの闇
hirachan
3
250
Weekly AI Agents News! 12月号 論文のアーカイブ
masatoto
0
150
最近のVisual Odometryと Depth Estimation
sgk
1
380
サーブレシーブ成功率は勝敗に影響するか?
vball_panda
0
490
第79回 産総研人工知能セミナー 発表資料
agiats
3
200
博士学位論文予備審査 / Scaling Telemetry Workloads in Cloud Applications: Techniques for Instrumentation, Storage, and Mining
yuukit
1
1.7k
ナレッジプロデューサーとしてのミドルマネージャー支援 - MIMIGURI「知識創造室」の事例の考察 -
chiemitaki
0
190
[輪講] Transformer Layers as Painters
nk35jk
4
620
テキストマイニングことはじめー基本的な考え方からメディアディスコース研究への応用まで
langstat
1
180
Tiaccoon: コンテナネットワークにおいて複数トランスポート方式で統一的なアクセス制御
hiroyaonoe
0
340
Global Evidence Summit (GES) 参加報告
daimoriwaki
0
230
Featured
See All Featured
Navigating Team Friction
lara
183
15k
Faster Mobile Websites
deanohume
305
30k
Bootstrapping a Software Product
garrettdimon
PRO
305
110k
GraphQLの誤解/rethinking-graphql
sonatard
68
10k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
28
2.2k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
44
7k
Designing on Purpose - Digital PM Summit 2013
jponch
117
7.1k
No one is an island. Learnings from fostering a developers community.
thoeni
20
3.1k
Fontdeck: Realign not Redesign
paulrobertlloyd
82
5.3k
Done Done
chrislema
182
16k
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
113
50k
Reflections from 52 weeks, 52 projects
jeffersonlam
348
20k
Transcript
Enabling Networked Knowledge ACKNOWLEDGEMENTS: This work was funded in part
by Science Foundation Ireland under Grant No. SFI/08/CE/I1380 (Lion-2). DRETA: EXTRACTING RDF FROM WIKITABLES Emir Muñoz, Aidan Hogan, Alessandra Mileo National University of Ireland, Galway MOTIVATION WIKITABLE SURVEY player http://dbpedia.org/resource/David_de_Gea http://dbpedia.org/resource/Rafael_Pereira_da_Silva_(footballer_born_1990) http://dbpedia.org/resource/Patrice_Evra …. http://dbpedia.org/resource/Fabio_Pereira_da_Silva http://dbpedia.org/resource/Tom_Cleverley http://dbpedia.org/resource/Darren_Fletcher PROPOSAL http://dbpedia.org/resource/Manchester_United_F.C. http://dbpedia.org/resource/England http://dbpedia.org/resource/Forward_(association_football) http://dbpedia.org/resource/Wayne_Rooney dbo:birthPlace dbp:currentclub dbp:position http://dbpedia.org/resource/Spain http://dbpedia.org/resource/Goalkeeper_(association_football) http://dbpedia.org/resource/David_de_Gea dbp:position http://dbpedia.org/resource/Brazil http://dbpedia.org/resource/Defender_(association_football) http://dbpedia.org/resource/Fabio_Pereira_da_Silva dbp:position … … (1) dbr:David_de_Gea dbo:birthPlace dbr:Spain . (2) dbr:Fabio_Pereira_de_Silva dbo:birthPlace dbr:Brazil . (3) dbr:Fabio_Pereira_de_Silva dbp:currentclub dbr:Manchester_United_F.C . SUGGESTED TRIPLES: SELECT ?player WHERE { ?player dbp:currentclub dbr:Manchester_United_F.C . } TABLE TAXONOMY: DISTRIBUTIONS: QUERY: RESULTS DEMO … http://emunoz.org/wikitables (1) EXTRACTED 34.9 MILLION UNIQUE & NOVEL TRIPLES FROM 1.14 MILLION WIKITABLES (8 MACHINES: 4GB RAM, 2.2 GHZ SINGLE CORE; 12 DAYS) (2) INITIAL EVALUATION: (MANUAL ANNOTATION; THREE JUDGES; 750 TRIPLES EACH) (3) MACHINE LEARNING CLASSIFIERS: (CONSENSUS GOLD STANDARD; VARIETY OF FEATURES) FROM 1.14 MILLION WIKITABLES: BAGGING DECISION TREES: SUPPORT VECTOR MACHINES: 1.14 MILLION WIKITABLES: 7.9 MILLION TRIPLES @81.5% PREC. 15.3 MILLION TRIPLES @72.4% PREC. … INCOMPLETE RESULTS!