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
52
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
42
Academic Writing: Hints and Tools
emunoz
0
120
Mining Cardinalities from Knowledge Bases
emunoz
0
130
Using Drug Similarities for Discovery of Possible Adverse Reactions
emunoz
0
83
A Hybrid Method for Rating Prediction Using Linked Data Features and Text Reviews
emunoz
0
140
On Learnability of Cardinality Constraints from RDF Data
emunoz
0
94
Minute Madness ESWC 2016
emunoz
0
83
Tensor Networks---a brief description
emunoz
0
57
A Linked Data-Based Decision Tree Classifier to Review Movies
emunoz
1
140
Other Decks in Research
See All in Research
HP (Hitto Point: 筆頭ポイント)
tanichu
0
720
FMP L3 Year 1 Project Proposal
haiinya
0
150
東工大Swallowプロジェクトにおける大規模日本語Webコーパスの構築
aya_se
12
6.5k
ICLR2024 LLMエージェントの研究動向
masatoto
6
1.9k
Source Code Diff Revolution (JetBrains Open Reading Club)
tsantalis
0
260
精神疾患患者のアクティビティデータを利用したリハビリテーションのためのシステムに関する研究
comfortdesignlab
0
140
訓練データ作成のためのCloudCompareを利用した点群の手動ラベリング
kentaitakura
0
540
ニフティのインナーソース導入事例 - InnerSource Commons #11
niftycorp
PRO
0
260
第12回全日本コンピュータビジョン勉強会:画像の自己教師あり学習における大規模データセット
naok615
0
520
Prompt Tuning から Fine Tuning への移行時期推定
icoxfog417
17
7k
DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials
tsurubee
0
370
Cross-Media Information Spaces and Architectures
signer
PRO
0
120
Featured
See All Featured
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
19
1.7k
Designing on Purpose - Digital PM Summit 2013
jponch
110
6.5k
Building an army of robots
kneath
300
41k
Imperfection Machines: The Place of Print at Facebook
scottboms
260
12k
Debugging Ruby Performance
tmm1
70
11k
Adopting Sorbet at Scale
ufuk
68
8.6k
A better future with KSS
kneath
231
16k
Building Your Own Lightsaber
phodgson
99
5.7k
A Modern Web Designer's Workflow
chriscoyier
689
190k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
14
1.5k
Put a Button on it: Removing Barriers to Going Fast.
kastner
58
3.1k
Embracing the Ebb and Flow
colly
80
4.1k
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!