FROM WORDS TO
SMART DATA PIECES
WORDS SMART
DATA
WORDS
WORDS
WORDS
searching...
Computing makes our life easier, helping us classify,
structure and ultimately make sense of data.
1
The thing is, to a machine a free flowing text is just a pile
of unstructured, heterogeneous, unreadable data. So, the
question for us is how can we help computers help us
with data and knowledge management? 2
CONCEPT
The answer is straightforward: we can help computers
help us by using semantic enrichment.
3
Rome
Milano
Tower of Pisa
Sounds too technical?
Don’t worry. Think of the Roman Empire. 4
Now try to guess what is the common thread between
Roman Empire and the easy-to-search and easy-to-use,
machine-readable pieces of data.
5
CONCEPT
In a word, it is interconnectedness. A rich system
of intelligent pathways throughout your content
management system and across the web. 6
W
ORDS
W
ORDS
WORDS
WORDSWORDS
W
ORDSW
ORDS
WORDSWORDSWORDS WORDS
WORDSWORDS
WORDSWORDSWORDSWORDSWORDS
WORDS W
ORDS
WORDSWORDS
W
ORDS W
ORDS
WORDSWORDS
W
ORDSW
ORDS
W
ORDS
WORDS
WORDS WORDS
WORDSWORDS
WORDS WORDSWORDS
WORDS WORDSWORDS
WORDSWORDS
WORDS
SMART
PIECES
OF DATA
When everything is interlinked, the interconnected parts
are more easily remixed, put together in new ways,
recombined, repurposed. Words become not only words,
but rather smart pieces of data. 7
Thus your content is able to travel across multiple channels,
platforms and systems. This in turn helps you connect the
dots, inform your insights, guide your research, uncover
hidden relationships.
Company Location
City Country
UK01/11/2014
type
establOn
locOn
type
type
type
partOf
LondonXYZ Bulgaria
8
Here’s how the technology works in 5 steps:
“Rome was the centre of the Roman Empire and there
were over 400,000 km of roman roads connecting the
provinces to Rome.
”
1 Text is extracted from articles, documents or any form
of unstructured data.
9
2
Rome was the centre of the Roman Empire and there
were over 400,000 km of roman roads connecting the
provinces to Rome.
After sentences are split, the important concepts and entities
(i.e.the proper nouns) are identified through dictionary word lists.
10
Roman EmpireRome
Capital of Italy
2.627 million (2012)
around 753 BC
1,285 km2
Population:
Founded:
Area:
Capitals:
Population:
Founded:
Area:
Rome was the centre of the Roman Empire
and there were over 400,000 km of roman roads
connecting the provinces to Rome.
3
Ravenna, Constantinople,
Rome
56.8 million (25 BC)
27 BC
Machine learning algorithms classify and disambiguate the
identified entities.
11
Relationships between the entities are also identified.
4
Roman Roads
Roman EmpireRome
hasin
incenterof
was the centre of the Roman Empire
and there were over 400,000 km of roman roads
connecting the provinces to Rome.
in center of
Rome
12
Additionally, the facts and the original reference to the articles
are indexed and stored with corresponding classifications and
relationships in a triplestore.
5
has_length
has_capital
Roman Empire
Rome
Roman Roads
400,000 km
Rome was the centre of the Roman Empire
and there were over 400,000 kmof roman roads
connecting the provinces to Rome.
has_infrastructure
is_center_of
13
With these 5 stepssemantic enrichment enables your
content to interconnect in a myriad of combinations and
thus brings a myriad of benefits for you and your business.
14
Semantic enrichment ​ brings you the benefits of​:
o reduced operational costs for content management
o less content mess and more accurate research
o better search and representation of your content (both within the
company and on the web)
o complex queries that go beyond keywords and interrelated ways of
navigating through content
o neatly stored (regularly updated) domain knowledge
o automatic aggregation, repurposing and reuse of content assets
15
Download our latest whitepaper:
Smarter Content with a Dynamic
Semantic Publishing Platform:
The Semantic Technologies that
Can Make Any Content Intelligent*
and learn how to convert your
content into revenue.
Intrigued by the idea of well-organized and cost-effective
management of your content assets?
16
* click to download
WE LOOK FORWARD TO HELPING YOU
MAKE SENSE OF YOUR DATA
AND CONVERT YOUR CONTENT
INTO REVENUE
www.ontotext.com
You can also reach us via email at
info@ontotext.com
and directly by calling
1-866-972-6686 (North America),
or +359 2 974 61 60 (Europe)

From Words to Smart Data Pieces

  • 1.
    FROM WORDS TO SMARTDATA PIECES WORDS SMART DATA WORDS WORDS WORDS
  • 2.
    searching... Computing makes ourlife easier, helping us classify, structure and ultimately make sense of data. 1
  • 3.
    The thing is,to a machine a free flowing text is just a pile of unstructured, heterogeneous, unreadable data. So, the question for us is how can we help computers help us with data and knowledge management? 2
  • 4.
    CONCEPT The answer isstraightforward: we can help computers help us by using semantic enrichment. 3
  • 5.
    Rome Milano Tower of Pisa Soundstoo technical? Don’t worry. Think of the Roman Empire. 4
  • 6.
    Now try toguess what is the common thread between Roman Empire and the easy-to-search and easy-to-use, machine-readable pieces of data. 5
  • 7.
    CONCEPT In a word,it is interconnectedness. A rich system of intelligent pathways throughout your content management system and across the web. 6
  • 8.
    W ORDS W ORDS WORDS WORDSWORDS W ORDSW ORDS WORDSWORDSWORDS WORDS WORDSWORDS WORDSWORDSWORDSWORDSWORDS WORDS W ORDS WORDSWORDS W ORDSW ORDS WORDSWORDS W ORDSW ORDS W ORDS WORDS WORDS WORDS WORDSWORDS WORDS WORDSWORDS WORDS WORDSWORDS WORDSWORDS WORDS SMART PIECES OF DATA When everything is interlinked, the interconnected parts are more easily remixed, put together in new ways, recombined, repurposed. Words become not only words, but rather smart pieces of data. 7
  • 9.
    Thus your contentis able to travel across multiple channels, platforms and systems. This in turn helps you connect the dots, inform your insights, guide your research, uncover hidden relationships. Company Location City Country UK01/11/2014 type establOn locOn type type type partOf LondonXYZ Bulgaria 8
  • 10.
    Here’s how thetechnology works in 5 steps: “Rome was the centre of the Roman Empire and there were over 400,000 km of roman roads connecting the provinces to Rome. ” 1 Text is extracted from articles, documents or any form of unstructured data. 9
  • 11.
    2 Rome was thecentre of the Roman Empire and there were over 400,000 km of roman roads connecting the provinces to Rome. After sentences are split, the important concepts and entities (i.e.the proper nouns) are identified through dictionary word lists. 10
  • 12.
    Roman EmpireRome Capital ofItaly 2.627 million (2012) around 753 BC 1,285 km2 Population: Founded: Area: Capitals: Population: Founded: Area: Rome was the centre of the Roman Empire and there were over 400,000 km of roman roads connecting the provinces to Rome. 3 Ravenna, Constantinople, Rome 56.8 million (25 BC) 27 BC Machine learning algorithms classify and disambiguate the identified entities. 11
  • 13.
    Relationships between theentities are also identified. 4 Roman Roads Roman EmpireRome hasin incenterof was the centre of the Roman Empire and there were over 400,000 km of roman roads connecting the provinces to Rome. in center of Rome 12
  • 14.
    Additionally, the factsand the original reference to the articles are indexed and stored with corresponding classifications and relationships in a triplestore. 5 has_length has_capital Roman Empire Rome Roman Roads 400,000 km Rome was the centre of the Roman Empire and there were over 400,000 kmof roman roads connecting the provinces to Rome. has_infrastructure is_center_of 13
  • 15.
    With these 5stepssemantic enrichment enables your content to interconnect in a myriad of combinations and thus brings a myriad of benefits for you and your business. 14
  • 16.
    Semantic enrichment ​brings you the benefits of​: o reduced operational costs for content management o less content mess and more accurate research o better search and representation of your content (both within the company and on the web) o complex queries that go beyond keywords and interrelated ways of navigating through content o neatly stored (regularly updated) domain knowledge o automatic aggregation, repurposing and reuse of content assets 15
  • 17.
    Download our latestwhitepaper: Smarter Content with a Dynamic Semantic Publishing Platform: The Semantic Technologies that Can Make Any Content Intelligent* and learn how to convert your content into revenue. Intrigued by the idea of well-organized and cost-effective management of your content assets? 16 * click to download
  • 18.
    WE LOOK FORWARDTO HELPING YOU MAKE SENSE OF YOUR DATA AND CONVERT YOUR CONTENT INTO REVENUE www.ontotext.com You can also reach us via email at info@ontotext.com and directly by calling 1-866-972-6686 (North America), or +359 2 974 61 60 (Europe)