Alessio Bosca (CELI) presented how CELI is exploiting linked data. Their focus is on speech applications, semantic search, text analytics, opinion mining and social media intelligence. The core technology used encompasses language processes such as language identification, morphological analyses and semantic analysis. CELI exploits the linked data in the LOD cloud a) as a user by making use of for NER, and b) as a provider for internal use and for crafting RDF artifacts. Two projects were addressed: a book project for the digital humanities and the Homer project for multilingual interfaces to assessing data from different public administration. From the work with linked open data the the LOD cloud community is advised to put more emphasis on truly linking of the datasets. With regard to the public sectors it is suggested that more data should be published as linked open data and that international standards should be used. The issue of publishing companies’ linked data under an open license was also addressed. The speaker made the point that besides the resistance to sharing, because of valid competitive concerns, company data is generally over-fitted to their solutions and clients. In other words, companies need to be able to manage ‘micro-domains’ which are regarded as less useful in general. Compromisingly it was suggested by the audience that companies should not answer the question why they do not publish their linked data, but what they could publish.

1. Linked Data for content analytics in Celi
Semantics 2014 - Leipzig
Alessio Bosca

2. Agenda
ü Presentation of Celi
ü Technologies (and what we do with
them)
ü Focus on LOD for content analytics
in Celi
ü … what we’d like to do
2

3. 1999
CELI srl was born
2002
Speech Technology
2006
BlogMeter
1999 2005 2010
2013
Korean Market
2011
Cross Library
2010
Milan, Rome,
Trento
3

4. 4 Seats
Torino
Milano
Trento
Roma
Italy
Belgium
France
Spain
Corea
Poland
50
Employees +
Collaborators
6 Markets
>100
Active clients
4
Business branches
15 Years of experience
NLP components
Speech technology
Social Media Intelligence
Digital Humanities
4

5. >50 Published papers 15 Research projects
Scuola Normale Superiore
Università di Torino
Università di Pisa
Università di Trento
Fondazione Bruno Kessler
Politecnico di Milano
6 Agreements with research centers
Relationships with the scientific community
5

6. 6
Core technology
opinion
mining,
mood and
sentiment
analysis
normalization
language
identification
NSW
processing morphological
tokenization
analysis
disambiguation
chunking and
phrasing
phonetic
transcription
with word
stress
semantic
clustering
automatic
classification
named entities

7. Techs
Guava
Kestrel
Virtuoso
OpenSource
7

8. 8
Clients
Semantic Solutions Speech Technology Social Media Monitoring

9. Linked (and/or Open) Data
Linked Data
Open Data
?
LOD
9

10. Private Sector: how Celi exploits L(O)D
• as user
LODs as linguistic resources for NER,
content enrichment, machine linking,
discovery search…
• as provider for the PA
publishing, data integration
• internal use
(e.g. assets management)
• crafting of RDF artifacts
for custom projects and applications
10

11. LOD for NER
• GENDER GUESSER
• LOCATION GUESSER
• ENTITY LINKER
• ETC .
11
INDEXER
DUMP
CELI TRIPLE STORES
INDEXES
Linguistic Analysis
SPARQL QUERIES
SEARCHER
CUSTOM RDF
WEBAPPS

12. Faceted Semantic Search
Browse through
documents
and contents
Relations between Facets
12

13. LOD for CLIR
THE AGROVOC
THESAURUS HAS
BEEN USED IN
THE
ORGANIC.LINGU
A PROJECT FOR
ONTOLOGY-BASED
CLIR
13

14. Sem-web techs for internal models
Information in the
CRUNCHED BOOK is
represented using
combinations of RDF
and GRAPH DBS
14

15. Public Sector: clear process …
acquire
data
set open
license
open
formats publish
15
Celi for the public sector
(CSI Piemonte):
the Homer project

16. (Public sector contd.) … but …
LACK
OF MONEY
USE OF “STANDARDS”
… hard
problems OPAQUE DATASETS
LACK
OF WILLINGNESS
POOR RDF/SPARQL
SUPPORT
16

17. Why companies’ RDF is not published
• It reflects customers’ needs • It reflects internal data models
HENCE à OVERFITTING:
Provocation
It would not be interesting nor usable
WAY OUTS:
having more standard models for particular micro-domains could permit their direct
(re)use by the private company (and hence the publication of enhanced versions)
17

18. Receipts
Public Sector: use “true” LOD technologies (RDF dumps and SPARQL endpoints)
Private companies: use standard data models, internally and for their artifacts
OpenData Community: please stress the linked in LOD!
The success of LOD is bound to the use of Linked Data
(as a technology)
The use of LD in the Private Sector will positively
feedback on the diffusion of the necessary expertise and
sensibility in the Public Sector too
18

19. Thank You!