SlideShare uma empresa Scribd logo
1 de 19
HOW CAN I TRANSFORM AN ONLINE
SERVICE TO TRULY MULTILINGUAL?
TYPICAL PROBLEMS
Online discovery services Agricultural domain
can I have more options?
why so many options?
why terminology is not correctly transformed?
can I search using terms in
my language?
why terminology is not transformed correclty?
WHAT ORGANIC.LINGUA PROJECT IS
PROPOSING
The common multilingual processing framework
A number of open source tools that could
be re-used
• AgLR can be used to share digital resources and to provide semantic and
multilingual annotation for them.
• Language Analytics can be used a) to wrap several language services such
as MS Bing, XEROX MT, MosesCore MT services b) to evaluate the quality
of the translation by providing a simple rating and c) to keep analytics
about all the translations.
• MoKi can be used to collaboratively develop KOSs and to expose them in
linked data format.
• agriMoodle can be used to share learning resources and courses and to
provide semantic and multilingual annotation for them
• Organic.Edunet portal infrastructure that can be re-used to develop a
multilingual online document discovery service
• Proxy module for Moses MT that can be used as a free alternative for MT
services for specific language pairs
• Machine Translation Caching module
• Tool for automatically matching concepts between multilingual Thesauri
(RDF SKOS format)
10 WAYS TO BECOME MULTILINGUAL
The Best Practices were
defined in the context of
www.organic-lingua.eu
project based on the
experience of developing a
truly multilingual Pan-
European online service, the
www.organic-edunet.eu
portal
10 ways to become truly multilingual
1. Rely on REST style
2. Localize your service
3. Rely on multilingual KOSs
4. Publish KOSs as linked data
5. Be domain specific
6. Select the best MT service
7. Enable multilingual search
8. Wrap language services
9. Keep analytics
10. Think of users
Rely on REST style
Follow a service oriented
approach in the
architecture of your
online service
Rely on REST style
✓ Follow a SOA
approach using REST
✓ Integrate easily new
language
technologies
✓ Integrate easily KOSs
to annotate your
resources and allow
navigation
✓ Cache information if
performance matters
Localize your front
end service
Follow the concepts of
the International web
design (i18n) to localize
your front end service
Localize your service
✓ Internationalization
✓ Do not use graphics
with text
✓ Localize all
components of the
portal e.g. generic
content, feedback
forms
✓ Use MT in interface
translation as a
supporting tool
Rely on
multilingual KOSs
Use and Manage
multilingual KOSs
centrally
Rely on multilingual KOSs
✓ Use multilingual KOSs
✓ Keep them centrally
✓ Manage them with
friendly open source tool
that can be used by
domain experts
✓ Allow collaborative KOSs
evolution
✓ Rely only on KOS’s id and
not on labels in your local
db
Publish KOSs as
linked data
Published all the KOSs
used in your online
service as linked data
Publish KOSs as linked data
✓ KOSs linking
✓ Link to external sources
✓ Use terms from external
KOSs in search
✓ Use KOSs for domain
adaptation
Be domain specific
The language services
should be domain
specific especially if your
online service targets a
particular sector
Be domain specific
✓ Collect domain
language resources
✓ Train language
services by using
domain specific
resources
✓ Use domain specific
widely accepted KOSs
Select the best MT
Select the best MT for
the domain of your
service
Select the best MT
✓ Compare the
different MT services
✓ Check open and free
solutions
✓ Check domain
adaptation
capabilities
✓ Perform in vitro
evaluation
✓ Ask users to help you
in evaluation
✓ Add a simple rating
for MT in your service
Multilingual
search
Allow users to search
using their native
language.
Multilingual search
✓ Keep in mind that
users know the
terminology in their
native language
✓ Translate queries
✓ Enrich your indexes
with domain specific
KOSs
✓ Put manual
enrichment first
Wrap language
services
Add a component in your
architecture that will
wrap the language
services
Wrap language services
✓ Different language
services for each
language
✓ Do not integrate
directly the language
services in your
portal
✓ Create a uniform
REST interface for all
the language services
✓ Share the same
wrapping component
among
Keep analytics
Analytics can help you in
understanding how the
language technologies
are used in your online
service
Keep analytics
✓ Track the origin of
your visitors
✓ Create a linguistic
profile of the users
✓ Use an analytics
component in your
architecture
✓ Add a simple rating
for MT in your
analytic services
Think of users
Always think of users
and their linguistic
profile
Think of users
✓ Study their
geographical
distribution
✓ Inform users about
automatic translation
✓ Allow users to disable
the automatic
translation in search
and browsing
✓ Enable feedback
about the automatic
translation
✓ Allow users to submit
improved translations
ORGANIC.LINGUA
ONLINE WORKSHOP
27/3/2014, 15:00 CET
http://wiki.organic-
lingua.eu/organic_lingua_online_workshop
It is important to
evaluate the MT services
before their use in your
online service
Organic.Lingua project
✓ ICT – PSP
✓ Just finished
✓ Check our project site
www.organic-lingua.eu
✓ Check our service
www.organic-edunet.eu
✓ Check our open source tools
http://wiki.organic-lingua.eu/
Open_Source_Tools

Mais conteúdo relacionado

Mais de Stoitsis Giannis (9)

How internet and open data transforms the agricultural sector (in greek)
How internet and open data transforms the agricultural sector (in greek)How internet and open data transforms the agricultural sector (in greek)
How internet and open data transforms the agricultural sector (in greek)
 
Facilitating regional growth through they use of open agricultural data
Facilitating regional growth through they use of open agricultural dataFacilitating regional growth through they use of open agricultural data
Facilitating regional growth through they use of open agricultural data
 
Open data: Showcases from agricultural domain
Open data: Showcases from agricultural domainOpen data: Showcases from agricultural domain
Open data: Showcases from agricultural domain
 
How e-infrastructure can contribute to Linked Germplasm Data
How e-infrastructure can contribute to Linked Germplasm DataHow e-infrastructure can contribute to Linked Germplasm Data
How e-infrastructure can contribute to Linked Germplasm Data
 
Intro to-technologies-Green-City-Hackathon-Athens
Intro to-technologies-Green-City-Hackathon-AthensIntro to-technologies-Green-City-Hackathon-Athens
Intro to-technologies-Green-City-Hackathon-Athens
 
Ag infra kream-presentation-7-6-2013
Ag infra kream-presentation-7-6-2013Ag infra kream-presentation-7-6-2013
Ag infra kream-presentation-7-6-2013
 
Cetaf ISTC Meeting: Natural-Europe Presentation
Cetaf ISTC Meeting: Natural-Europe PresentationCetaf ISTC Meeting: Natural-Europe Presentation
Cetaf ISTC Meeting: Natural-Europe Presentation
 
Requirements for Processing Datasets for Recommender Systems
Requirements for Processing Datasets for Recommender SystemsRequirements for Processing Datasets for Recommender Systems
Requirements for Processing Datasets for Recommender Systems
 
Organic.lingua presentation cer_organic
Organic.lingua presentation cer_organicOrganic.lingua presentation cer_organic
Organic.lingua presentation cer_organic
 

Último

EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 

Último (20)

Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 

OL best-practices-online-workshop

  • 1. HOW CAN I TRANSFORM AN ONLINE SERVICE TO TRULY MULTILINGUAL?
  • 3. Online discovery services Agricultural domain can I have more options? why so many options? why terminology is not correctly transformed? can I search using terms in my language? why terminology is not transformed correclty?
  • 5. The common multilingual processing framework
  • 6. A number of open source tools that could be re-used • AgLR can be used to share digital resources and to provide semantic and multilingual annotation for them. • Language Analytics can be used a) to wrap several language services such as MS Bing, XEROX MT, MosesCore MT services b) to evaluate the quality of the translation by providing a simple rating and c) to keep analytics about all the translations. • MoKi can be used to collaboratively develop KOSs and to expose them in linked data format. • agriMoodle can be used to share learning resources and courses and to provide semantic and multilingual annotation for them • Organic.Edunet portal infrastructure that can be re-used to develop a multilingual online document discovery service • Proxy module for Moses MT that can be used as a free alternative for MT services for specific language pairs • Machine Translation Caching module • Tool for automatically matching concepts between multilingual Thesauri (RDF SKOS format)
  • 7. 10 WAYS TO BECOME MULTILINGUAL
  • 8. The Best Practices were defined in the context of www.organic-lingua.eu project based on the experience of developing a truly multilingual Pan- European online service, the www.organic-edunet.eu portal 10 ways to become truly multilingual 1. Rely on REST style 2. Localize your service 3. Rely on multilingual KOSs 4. Publish KOSs as linked data 5. Be domain specific 6. Select the best MT service 7. Enable multilingual search 8. Wrap language services 9. Keep analytics 10. Think of users
  • 9. Rely on REST style Follow a service oriented approach in the architecture of your online service Rely on REST style ✓ Follow a SOA approach using REST ✓ Integrate easily new language technologies ✓ Integrate easily KOSs to annotate your resources and allow navigation ✓ Cache information if performance matters
  • 10. Localize your front end service Follow the concepts of the International web design (i18n) to localize your front end service Localize your service ✓ Internationalization ✓ Do not use graphics with text ✓ Localize all components of the portal e.g. generic content, feedback forms ✓ Use MT in interface translation as a supporting tool
  • 11. Rely on multilingual KOSs Use and Manage multilingual KOSs centrally Rely on multilingual KOSs ✓ Use multilingual KOSs ✓ Keep them centrally ✓ Manage them with friendly open source tool that can be used by domain experts ✓ Allow collaborative KOSs evolution ✓ Rely only on KOS’s id and not on labels in your local db
  • 12. Publish KOSs as linked data Published all the KOSs used in your online service as linked data Publish KOSs as linked data ✓ KOSs linking ✓ Link to external sources ✓ Use terms from external KOSs in search ✓ Use KOSs for domain adaptation
  • 13. Be domain specific The language services should be domain specific especially if your online service targets a particular sector Be domain specific ✓ Collect domain language resources ✓ Train language services by using domain specific resources ✓ Use domain specific widely accepted KOSs
  • 14. Select the best MT Select the best MT for the domain of your service Select the best MT ✓ Compare the different MT services ✓ Check open and free solutions ✓ Check domain adaptation capabilities ✓ Perform in vitro evaluation ✓ Ask users to help you in evaluation ✓ Add a simple rating for MT in your service
  • 15. Multilingual search Allow users to search using their native language. Multilingual search ✓ Keep in mind that users know the terminology in their native language ✓ Translate queries ✓ Enrich your indexes with domain specific KOSs ✓ Put manual enrichment first
  • 16. Wrap language services Add a component in your architecture that will wrap the language services Wrap language services ✓ Different language services for each language ✓ Do not integrate directly the language services in your portal ✓ Create a uniform REST interface for all the language services ✓ Share the same wrapping component among
  • 17. Keep analytics Analytics can help you in understanding how the language technologies are used in your online service Keep analytics ✓ Track the origin of your visitors ✓ Create a linguistic profile of the users ✓ Use an analytics component in your architecture ✓ Add a simple rating for MT in your analytic services
  • 18. Think of users Always think of users and their linguistic profile Think of users ✓ Study their geographical distribution ✓ Inform users about automatic translation ✓ Allow users to disable the automatic translation in search and browsing ✓ Enable feedback about the automatic translation ✓ Allow users to submit improved translations
  • 19. ORGANIC.LINGUA ONLINE WORKSHOP 27/3/2014, 15:00 CET http://wiki.organic- lingua.eu/organic_lingua_online_workshop It is important to evaluate the MT services before their use in your online service Organic.Lingua project ✓ ICT – PSP ✓ Just finished ✓ Check our project site www.organic-lingua.eu ✓ Check our service www.organic-edunet.eu ✓ Check our open source tools http://wiki.organic-lingua.eu/ Open_Source_Tools

Notas do Editor

  1. Portal owners are currently straggling to transform their service to truly multilingual. This is not a trivial task as
  2. Portal owners are currently straggling to transform their service to truly multilingual. This is not a trivial task as
  3. Portal owners are currently straggling to transform their service to truly multilingual. This is not a trivial task as
  4. Portal owners are currently straggling to transform their service to truly multilingual. This is not a trivial task as