Copyright 2009 Digital Enterprise Research Institute. All rights reserved.
The Semantic Web vision & Linked Data
Multi-disciplinary perspective
Linked Data, IR, NLP
Case study: Treo
Talking to the Linked Data Web
Semantic application patterns
Take-away message
2001:
Software which is able to
understand meaning
(intelligent, flexible)
Leveraging the Web for
information scale
What was the plan to
achieve it?
Build a Semantic Web
Stack
Which covers both
representation and
reasoning
Adoption:
No significant data
growth
Ontologies are not
straightforward to
build:
People are not
familiriazed with the
tools and principles
Difficult to keep
consistency at Web scale
Scalability
Problems:
Consistecy
Scalability
Logic World
Web World
The Web as a Huge Database
Fundamental step for data
creation
2006:
Where is the intelligence and
flexibility?
We will be back to this point
in a minute
Data Model Features:
Graph-based data model
Extensible schema
Entity-centric data integration
Specific Features:
Designed over open Web standards
Based on the Web infrastructure (HTTP, URIs)
Positives:
Solid adoption in the Open Data context
(eGovernment, eScience, etc,...)
Existing data is relevant (you can build real
applications)
Negatives:
Data consumption is a problem
Data generation beyond databases
mapping/triplification is also a problem
Still far from the Semantic Web vision
How to address the previous challenges?
Linked Data:
Web-scale structured data representation
Information Retrieval:
Search, approximation, ranking strategies
Scalability
Natural Language Processing (NLP):
Analysing natural language
Semantic approximation (distributional semantics)
IBM Watson approach
From which university did the wife of
Barack Obama graduate?
With Linked Data we are still in the DB world
With Linked Data we are still in the DB world
(but slightly worse)
From which university did the wife of Barack Obama graduate?
): Direction, path
Demonstration
Transform natural language queries into triple patterns
Steps:
Entity Recognition
Dependency parsing
Query Pattern detection
Query Planning
“From which university did the wife of Barack Obama graduate?”
prep(graduate-10, From-1)
det(university-3, which-2)
pobj(From-1, university-3)
aux(graduate-10, did-4)
det(wife-6, the-5)
nsubj(graduate-10, wife-6)
prep(wife-6, of-7)
nn(Obama-9, Barack-8)
pobj(of-7, Obama-9)
root(ROOT-0, graduate-10)
From/IN
which/WDT
university/NN
did/VBD
the/DT
wife/NN
of/IN
Barack/NNP
Obama/NNP
graduate/VB
?/.
Using NLP
Using NLP
Query:
Entity Search:
Build an entity index (instances)
Extract terms from URIs and index the terms using your
favourite IR framework
Search instances by keywords
Using IR
Using IR
Query
Linked Data
Web
Use distributional semantics to semantically match
query terms to predicates and classes
Distributional principle: Words that co-occur together
tend to have related meaning
Allows the creation of a comprehensive semantic model from
unstructured text
Based on statistical patterns over large amounts of text
No human annotations
Distributional semantics can be used to compute a
semantic relatedness measure between two words
Using NLP
and IR
Computation of a measure of “semantic proximity”
between two terms
Allows a semantic approximate matching between
and
It supports a reasoning-like behavior based on the
knowledge embedded in the corpus
Using NLP
and IR
Query
Linked Data
Web
Using NLP
and IR
Which properties are
semantically related to ‘wife’?
Using NLP
and IR
Query
Linked Data
Web
Using NLP
and IR
Query
Linked Data
Web
Query
Linked Data
Web
Using NLP
and IR
Semantic approximation in databases (as in any IR
system): semantic best-effort
Need some level of user disambiguation,
refinement and feedback
As we move in the direction of semantic systems
we should expect the need for principled dialog
mechanisms (like in human communication)
Pull the the user interaction back into the system
Using NLP
and IR
Derived from the experience developing Treo
Not restricted to queries over Linked Data
The following list is not intended to be complete
Pattern #1: Maximize the amount of knowledge in
your semantic application
Meaning interpretation depends on knowledge
Using LOD: DBpedia, Freebase, YAGO can give you
a very comprehensive set of instances and their
types
Wikipedia can provide you a comprehensive
distributional semantic model
Pattern #2: Allow your database to grow
Dynamic schema
Entity-centric data integration
Pattern #3: Once the database grows in complexity
use semantic search instead of structured queries
Instances can be used as pivot entities to reduce
the search space
They are easier to search
Higher specificity and lower vocabulary variation
Pattern #4: Use distributional semantics and
semantic relatedness for a robust semantic
matching
Distributional semantics allows your application to
digest (and make use of) large amounts of
unstructured information
Multilingual solution
Can be complemented with WordNet
Pattern #5: POS-Tags, Syntactic Parsing + Rules will
go a long way to interpret natural language queries
and sentences
Use them to explore the regularities in natural
language
Define a scope for natural language processing in
your application (restrict by domain, syntactic
complexity)
These tools are easy to use and quite robust (at
least for English)
Pattern #6: Provide a user dialog mechanism in the
application
Improve the semantic model with user feedback
Part of the Semantic Web vision can be addressed
today with a multi-disciplinary perspective
Linked Data, IR and NLP
You can build your own IBM Watson-like application
Both data and tools are available and ready to use:
the barrier is the mindset
Large opportunity for new solutions
NLP
WordNet
VerbNet
Stanford parser
C&C parser/Boxer
NLTK
DBpedia Spotlight
Gate
UIMA
IR
Lucene/Solr
Terrier
Datasets
DBpedia
Freebase
YAGO
Tools that will be
available soon:
Treo
Treo-ESA
Graphia
André Freitas, Edward Curry, João Gabriel Oliveira, Sean O'Riain,
. IEEE Internet
Computing, Special Issue on Internet-Scale Data, 2012.
André Freitas, Edward Curry, João Gabriel Oliveira, Sean O'Riain,
International Journal of Semantic Computing (IJSC),
2012.
André Freitas, Sean O'Riain, Edward Curry,
. 27th ACM Applied Computing Symposium, Semantic Web and Its
Applications Track, 2012.
André Freitas, João Gabriel Oliveira, Sean O'Riain, Edward Curry, João Carlos Pereira da
Silva, In
Proceedings of the 16th International Conference on Applications of Natural Language to
Information Systems (NLDB) 2011.
André Freitas, Danilo S. Carvalho, João Carlos Pereira da Silva, Sean O'Riain, Edward Curry, A
Semantic Best-Effort Approach for Extracting Structured Discourse Graphs from Wikipedia. In
Proceedings of the 1st Workshop on the Web of Linked Entities (WoLE 2012) at the 11th
International Semantic Web Conference (ISWC), 2012
andrefreitas.org
andre (dot) freitas – at – deri (dot) org