http://www.smart-cities.eu/model.html 2 A large amount of Open - - PowerPoint PPT Presentation

▶
http smart cities eu model html
SMART_READER_LITE
LIVE PREVIEW

http://www.smart-cities.eu/model.html 2 A large amount of Open - - PowerPoint PPT Presentation

Oct 08, 2022 166 likes •359 views

Fedelucio Narducci*, Matteo Palmonari *, Giovanni Semeraro *DISCO, University of Milan-Bicocca, Italy Department of Computer Science, University of Bari Aldo Moro, Italy ! !"#$%&' " !('' AI for Smart Cities Workshop #

slide-1
SLIDE 1

Fedelucio Narducci*, Matteo Palmonari*, Giovanni Semeraro°

*DISCO, University of Milan-Bicocca, Italy

°Department of Computer Science, University of Bari Aldo Moro, Italy

!!"#$%&' "!('' #&&!))'*'''''''''''''''''' $!+),$#-./#%,$'' +!)!#+&0'1+,23'45$6,$.,'7!--,8'

093:;;<<<=>.=2$.(#=.6;?)<#3''

AI for Smart Cities Workshop AI*IA 2013 - 25th Year Anniversary XIII Conference Turin (Italy), December 5, 2013

slide-2
SLIDE 2

2

http://www.smart-cities.eu/model.html

slide-3
SLIDE 3
  • A large amount of Open Government Data in

many languages*:

  • 1,000,000+ datasets published online (February 2013)
  • 40 different countries
  • 24 different languages

3

*http://logd.tw.rpi.edu/iogds_data_analytics

slide-4
SLIDE 4
  • Government service catalogs are part of

the LOD cloud

  • Effective Service Delivery (ESD)-toolkit
  • European Local Government Service List (LGSL)
  • 2000+ interlinked public services in 6 languages

4

slide-5
SLIDE 5
  • Advantages for PAs
  • Compare local service offerings with best practices in other countries
  • Support interoperability among PAs of different countries and other

service providers

  • Enrich service descriptions with additional information via links to LGSL

(e.g., link to life event ontologies)

  • Advantages for citizens
  • Find eGov services when in a foreign country
  • Towards cross-language service access

5

Costly and Error Prone Activity

Catalogs of several hundreds of services

slide-6
SLIDE 6

! sameAs links

6

  • Challenging cross-language matching

problem

  • Most of the approaches:
  • use structural information [Spohr et al.

2011, Fu et al. 2011, Wang et al. 2009] or long textual descriptions [Knoth et al. 2011]

  • r report problems when automatic

translation returns descriptions with heterogeneous vocabulary [Hertling & Paulheim 2012]

Semantic heterogeneity

  • not a mere “translation”

problem

  • cultural bias

Ultra-short descriptions

slide-7
SLIDE 7
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

7

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

TRY IT @ http://siti-rack.siti.disco.unimib.it:8080/croser/

slide-8
SLIDE 8
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

8

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

slide-9
SLIDE 9
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

9

  • Load a catalog

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

slide-10
SLIDE 10
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

10

  • Load a catalog
  • Select a source

service

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

slide-11
SLIDE 11
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

11

  • Load a catalog
  • Look at the retrieved

services (link recommendations)

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

  • Select a source

service

slide-12
SLIDE 12
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

12

  • Load a catalog
  • Link

SKOS broader / exact / narrower

match

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

  • Select a source

service

  • Look at the retrieved

services (link recommendations)

slide-13
SLIDE 13
  • CroSeR
  • A tool to support the linkage of a source eGov service catalog

represented in any language to a target catalog represented in English

  • Based on automatic translation and Explicit Semantic Analysis

13

Web tool to support the linkage of a source eGov service catalog represented in any language to a target catalog represented in English Based on Machine Translation and Explicit Semantic Analysis (ESA)

slide-14
SLIDE 14

14

Machine Translation of Service Descriptions Extraction of ESA-based representations and indexing (Vector Space Model) Top-k Service Retrieval by Cosine Similarity

slide-15
SLIDE 15

Technique able to provide a fine-grained semantic representation of natural language texts in a high-dimensional space of comprehensible concepts derived from Wikipedia [GM06]

[GM06] E. Gabrilovich and S. Markovitch. Overcoming the Brittleness Bottleneck using Wikipedia: Enhancing Text Categorization with Encyclopedic Knowledge. In Proceedings of the 21th National Conf. on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, pages 1301–1306. AAAI Press, 2006. @#$60!+#'

A,+->' A#+'BB' C#$!' D,$>#' B)-#$>'

A.E.3!>.#'F.!<!>'#)'#$'%&'%(%)*'G' #'&,--!&%,$',H'?+,'&,$&!36)'

15 15

slide-16
SLIDE 16
  • CroSeR finds matchings that cannot be discovered by

machine translation + keyword comparison

  • CroSeR’s recommendations can support the users to refine the

links

16

GT:“Absentee Ballot”

slide-17
SLIDE 17
  • Model and Experimental Evaluation @ISWC 2013
  • F. Narducci, M. Palmonari, G. Semeraro. Cross-Language Semantic

Retrieval and Linking of E-Gov Services."The Semantic Web - ISWC 2013 - 12th International Semantic Web Conference, Sydney, NSW, Australia, October 21-25, 2013, LNCS 8219, 130-145, Springer, 2013

  • System Demo @ECIR 2014
  • F. Narducci, M. Palmonari, G. Semeraro. CroSeR: Cross-language

Semantic Retrieval of Open Government."36th European Conference on Information Retrieval, Amsterdam, the Netherlands, April 13-16, 2014. To Appear

17

slide-18
SLIDE 18

ECIR 2014 live demo: http://siti-rack.siti.disco.unimib.it:8080/croser/

18