Realtime crowdsourced translation for emergency response and beyond
Upcoming SlideShare
Loading in...5
×
 

Realtime crowdsourced translation for emergency response and beyond

on

  • 3,207 views

 

Statistics

Views

Total Views
3,207
Views on SlideShare
3,205
Embed Views
2

Actions

Likes
0
Downloads
30
Comments
0

1 Embed 2

http://bildung.posterous.com 2

Accessibility

Categories

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Realtime crowdsourced translation for emergency response and beyond Realtime crowdsourced translation for emergency response and beyond Presentation Transcript

  • Robert Munro
    Stanford University & Energy for Opportunity
    Workshop on Crowdsourcing and Translation
    10 June 2010
    Realtime crowdsourced translation for emergency response and beyond
  • Where I’ve sourced crowds
    Industry
    Research
    Esp Psycholinguistics Munro et al 2010)
    Social development
  • Daily potential language exposure
    On a given day, what is the average number of languages that someone could potentially hear?
    How has this changed?
    # of languages
    Year
    View slide
  • Daily potential language exposure
    # of languages
    Year
    View slide
  • Daily potential language exposure
    # of languages
    Year
  • Daily potential language exposure
    # of languages
    Year
  • Daily potential language exposure
    You can make a realtime difference in the life of anyone you can communicate with
    We will never be so under-resourced to do this as we are right now
    But we can leverage many of the same technologies to crowdsource
  • Haiti, January 12
    Text messaging (SMS) is the dominant form of remote communication in Haiti
    The existing emergency response systems failed
    Most text messages were getting through
    A team of people came together quickly, all connected by Josh Nesbit of FrontlineSMS:Medic, to put together an SMS-based emergency response system
    We launched in under 48 hours
  • The responders don’t speak Kreyol
    FanmimwennanKafou, 24 Cote Plage, 41A bezwenmanjeakdlo
    MounkwensenanSakreKènanPòtoprens
    Ti ekipmanLopital General genyenyopakaminmfè 24 è
    Fanm gen tranche poufè yon pititnanDelmas 31
  • The responders don’t speak Kreyol
    FanmimwennanKafou, 24 Cote Plage, 41A bezwenmanjeakdlo
    MounkwensenanSakreKènanPòtoprens
    Ti ekipmanLopital General genyenyopakaminmfè 24 è
    Fanm gen tranche poufè yon pititnanDelmas 31
    • My family in Carrefour, 24 Cote Plage,41A needs food and water
    • People trapped in Sacred Heart Church, PauP
    • General Hospital has less than 24 hrs. supplies
    • Undergoing children delivery Delmas 31
  • Making a difference, from anywhere
    Translate 1 message = help 1 person
  • Messages: ~1000 per day
  • The process
  • The process
  • The process
    Average turnaround = 10 mins
  • At launch – utilizing volunteers
    Coordinate response
    Response
    Message to ‘4636’
    Translation and geo-location
    @Tufts
    Refine coordinates and identify actionable items
    Volunteer translators
  • Today – creating jobs
    Coordinate response
    Response
    Message to ‘4636 / 177’
    Translation and geo-location
    @Tufts
    Refine coordinates and identify actionable items
    Paid workers in Haiti
  • Collaborating organizations
  • Local knowledge counts
    Apo
    Dalila
    Haiti responders
    (18.4957, -72.3185)
    Workers collaborating to find locations:
    Dalila: I need Thomassin Apo please
    Apo: Kenscoff Route: Lat: 18.495746829274168, Long:-72.31849193572998
    Apo: This Area after Petion-Ville and Pelerin 5 is not on Google Map. We have no streets name
    Feedback from responders:
    "just got emergency SMS, child delivery,USCG are
    acting, and, the GPS coordinates of the location we
    got from someone of your team were 100% accurate!"
    The ability for someone to make a real-time difference at any other place in the world:
    Apo: I know this place like my pocket
    Dalila: thank God u was here
    ‘here’ = anywhere
  • Local knowledge counts
    “Rue Casseus no 9 gen yon santkap bay swenakmounkiblese e mounkibrile”
    Street Casseus no 9, there is a center that helps people that are wounded or burnt
    Marc, Union Haiti:
    “I will pass it on that is my cousins hospital.”
  • A person alone is not in a crowd
  • Ushahidi – Jan 14
  • Ushahidi – Jan 17
  • Ushahidi – Jan 17
  • Feedback - responders
    • Clark Craig of the Marine Corps:
    • “I cannot overemphasize to you what the work of the Ushahidi/Haiti has provided. It is saving lives every day.”
    • Secretary of State Hillary Clinton:
    • “The technology community has set up interactive maps to help us identify needs and target resources. And on Monday, a seven-year-old girl and two women were pulled from the rubble of a collapsed supermarket by an American search-and-rescue team after they sent a text message calling for help.”
    • Craig Fulgate, FEMA Task Force:
    • “[The] Crisis Map of Haiti represents the most comprehensive and up-to-date map available to the humanitarian community.”
    • Ushahidi@Tufts
    • “The World Food Program delivered food to an informal camp of 2500 people, having yet to receive food or water, in Diquini to a location that 4636 had identified for them.”
  • >1000 Volunteers
    Apo:
    “When I found out about the project I thought it was a really good thing because I could help people, instead of just donating to charity”
    Sarah, Union Haiti:
    “You kept us going”
  • Crowdsourced mapping – Jan 12
  • Crowdsourced mapping – Jan 23
  • Preparing for the future
    Microsoft Research have built new MT models with the SMS (Lewis 2010)
    Issues for MT
    Needed to re-translated (too much paraphrasing)
    Needed to normalize (too many abbreviations)
  • NLP for social development
    Bantu
    Beyond Haiti and emergency response
    Those with the least resources have the most to gain
    Chichewa
  • Professional communications
    Partnering with FrontlineSMS:Medic and a clinic in rural Malawi
    Classifying medical text messages (Munro and Manning 2010)
  • Why apply NLP to medical SMS?
    Identify outbreaks early
    Malaria Prevalence Model, MARA
    Route important data quickly
    Save time
    2 doctors for 250,000 patients
    = 5 seconds per patient per year
  • Variation is the norm
    Keyword-based models are suboptimal
  • Example
  • The potential
    medicine, banking, market information, literacy …
    # of languages
    Year
  • Thank you
    References
    Lewis, Will. 2010. Haitian Creole: How to Build and Ship an MT Engine from Scratch in 4 days, 17 hours, & 30 minutes. Annual Meeting of the European Association for Machine Translation
    Munro, Robert. 2010. Haiti emergency response: the power of crowdsourcing and SMS. Relief 2.0 in Haiti
    Munro, Robert, Steven Bethard, Victor Kuperman, Vicky Tzuyin Lai, Robin Melnick, Christopher Potts, Tyler Schnoebelen and Harry Tily. 2010. Crowdsourcing and language studies: the new generation of linguistic data. Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk.
    Munro, Robert and Christopher Manning. 2010. Subword Variation in Text Message Classification. Annual Conference of the North American Chapter of the Association for Computational Linguistics