SlideShare une entreprise Scribd logo
1  sur  33
Understanding Community Needs: Scalable
SMS Processing for UNICEF Nigeria and
Burundi
Jessica Long
Senior software engineer at Idibon
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program, and Idibon’s collaboration
• Lessons learned from automatic labeling in English and
minority languages
• Conclusions
Acknowledgements
• Robert Munro, CEO of Idibon
• Caroline Barebwoha, U-Report Nigeria project lead
• Aboubacar Kampo, U-Report Nigeria project lead
• Sarah Atkinson, U-Report Burundi project lead
• Kidus Fisaha Asfaw, Global head of U-Report
• Evan Wheeler, CTO of UNICEF Innovation / RapidPro
• Nicholas Gaylord, data scientist at Idibon
My background
Symbolic Systems BS
Computer Science MS
Health systems
manager in
rural Burundi
Internationalization
engineer
Second
language
acquisition
research
NLP engineer
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program, and Idibon’s collaboration
• Lessons learned from automatic labeling in English and
minority languages
• Conclusions
What is Natural Language Processing (NLP)?
Natural language processing is a branch of
artificial intelligence specifically concerned with
making automatic judgments about free text
Flavors of NLP
• Automatic categorization
• Machine translation
• Named entity recognition
• Sentiment Analysis
• Semantic Role Labeling
• Opinion Mining
• Parsing
• Question Answering
• Search
– 15% of Google’s daily search queries
have never been issued before!
• Part of Speech Tagging
• Textual Entailment
• Discourse Analysis
• Natural language
Generation
• Speech Recognition
• Word sense
disambiguation
• Text summarization
Underlying algorithms
• Semi-supervised machine learning
– Start with labeled training data that’s similar to what you
want to generate
– Use this to “teach” the computer what features to look for
when making a decision about the text
Cat Cat
Cat
???
Dog Dog
Dog
Training set Predictio
n
Semi-supervised machine learning example
• “Using Wikipedia for Automatic Word Sense Disambiguation,”
by Rada Mihalcea (2007)
Paris, France
Paris, Texas
Paris, France Paris, France
Paris, Texas
Tokenization and feature extraction (n-grams)
“tomb”, “of”, “the”, “unknown”, “soldier”,
“beneath”, “arc”, “de”, “triomphe”
“tomb of”, “of the”, “the unknown”,
“unknown soldier”, “beneath the”, “the
arc”, “arc de”, “de triomphe”
“tomb of the”, “of the unknown”, “the
unknown solider”, “unknown soldier
beneath”, “beneath the arc”, “the arc
de”, “arc de triomphe”
Other features
- Punctuation
- Stemming
- Parsing
- Capitalization
- Dictionary matching
- Stopwords
- …
Paris, France
Source text
Source label
Extracted features
Who uses NLP?
Apple’s Siri does
speech recognition on
human voices, as well
as question answering
IBM Watson answers
Jeopardy questions
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program, and Idibon’s collaboration
• Lessons learned from automatic labeling in English and
minority languages
• Conclusions
Language resources for UNICEF Uganda
30+ Languages Spoken in Uganda
Google Translate Supported Languages
Why is NLP difficult for minority
languages?
• Lots of code-switching breaks usual paradigm of language-
specific textual analysis
• Lack of existing digital tools: spell check, autocomplete,
access to internet
• Minority language speakers lack purchasing power
• Tokenization
– Consider:
• “ntibazoronka.”: “nta” “i” “ba” “zo” “ronka” “.” (Kirundi)
• “they will not obtain.”: “they” “will” “not” obtain” “.” (English)
• Encoding issues
– “I can text you a pile of poo , but I can’t write my name” by Aditya
Mukerjee in Model View Culture
But most of all. . .
• Minority languages lack appropriate training datasets.
– They tend to be primarily spoken, and lack the digital and
even written content necessary for statistical machine
learning
• Google Translate relies on parallel corpora from UN
proceedings to help create machine translation products
– The UN does not dual broadcast in Wolof.
• Textual reviews matched to star ratings on Yelp helps
researchers calibrate sentiment analysis
– Yelp is literally non-functional in most of Africa.
“Raw data is an oxymoron.”
- Lisa Gitelman
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program, and Idibon’s collaboration
• Lessons learned from automatic labeling in English and
minority languages
• Conclusions
Curation of language data, old & new
Compiled by Webster
Collective wisdom, at scale
Compiled by experts,
Supplemented by OED Reading Programme
* Shout out! Go see Martin
Benjamin’s talk on The
Kamusi Project tomorrow
at 13:45, for more
information on dictionary
curation
Creating new structured data with
crowdsourcing
• “Are two heads better than one? Crowdsourced
translation via a two-step collaboration of non-
professional editors and translators”, Yan et al
– Creating parallel corpuses with crowd workers is much
faster and cheaper than using professional translators
• Now, more than ever, we have the ability to rapidly
create new labeled language data
– …as long as we can find proficient writers of minority
languages with digital literacy, electricity, and internet
access
Cell phone access
• Nearly 6 billion people in the world have
access to a cell phone
• In 2013, the UN famously reported that more
people have access to a cell phone than to a
toilet
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program, and Idibon’s collaboration
• Lessons learned from Idibon’s automatic labeling in English
and minority languages
• Conclusions
UNICEF’s U-Report
• Crowd wisdom, in real time, in developing countries
• In 2012, UNICEF Innovation team started building a real-
time SMS polling service for UNICEF Uganda. As of 2015, U-
Report operates in over 15 countries
• Polls are sent out once a week on topics like:
– Has ur community addressed social inclusion issues affecting
women, youth, and children?
– If you get water from a well, borehole, or community tap, is it
working today?
– Go to your local health center and tell us: Do they give free HIV
/ AIDS tests? Report YES or NO and HEALTH CENTER NAME
UNICEF’s U-Report
• Eventually, UNICEF started receiving urgent, unsolicited
messages
– FLOOD.villages of X, Y sub.county suffering.
• UNICEF Nigeria alone now receives 10,000+ unsolicited
messages per day
• UNICEF needs a way to:
– Identify topically relevant messages to share with specific
partners
– Prioritize which messages to respond to first
• Idibon labels messages with urgency, category label,
and language, in real time
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program
• Lessons learned from Idibon’s automatic labeling in
English and minority languages
• Conclusions
Lesson #1: It’s difficult to predict how many
new people will use your product / service
when you start supporting a new language
Non-English Languages of Nigeria
0
5
10
15
20
25
30
Lesson #1: It’s difficult to predict how many
new people will use your product / service
when you start supporting a new language
# unsolicited
Hausa messages
per day
Hausa polls begin * But we don’t see the
same effect for Yoruba
Lesson #2: Language mixing in an African
context has different considerations for
classification algorithms vs European
language code-switching
• Downside: complex
tokenization
• Upside: radically different
word structure
Lesson #3: Geopolitical context affects how
we interpret short messages, and it’s
constantly changing
Lesson #4: Mutually exclusive categories
are elusive. To automatically label
messages is to discover the endless
ambiguity in human discourse.
- Is a washed out road more related to infrastructure or personal safety?
- Is education scoped to a particular time in life? Does post-graduate
education count? What about education outside of a scholastic context?
- If a town’s full name is “Mbale Village,” is “Mbale” a valid place name?
- How specific do messages need to be to constitute a security threat? Does
“these days some of our young people are not safe” count?
Overview
• Who’s involved in this project?
• What is Natural Language Processing (NLP)?
• What are the challenges of creating NLP for minority
languages and multilingual societies?
• How has the digital age changed how we curate language
data?
• UNICEF’s U-Report program, and Idibon’s collaboration
• Lessons learned from automatic labeling in English and
minority languages
• Conclusions
Conclusions
• Crowdsourcing, machine learning, and the
proliferation of cell phones make amazing new
communication tools and digital language
data possible
• Invest in translators and analysts
Thank you!

Contenu connexe

Similaire à Understanding Community Needs: Scalable SMS Processing for UNICEF Nigeria and Burundi

Fonelex Keynote
Fonelex KeynoteFonelex Keynote
Fonelex Keynote
ssorden
 

Similaire à Understanding Community Needs: Scalable SMS Processing for UNICEF Nigeria and Burundi (20)

Co-design-ee5-emer
Co-design-ee5-emerCo-design-ee5-emer
Co-design-ee5-emer
 
Sprache rettet Leben, Translators without Borders - Content Marketing Tuesday...
Sprache rettet Leben, Translators without Borders - Content Marketing Tuesday...Sprache rettet Leben, Translators without Borders - Content Marketing Tuesday...
Sprache rettet Leben, Translators without Borders - Content Marketing Tuesday...
 
Research sketchbook - Interaction Module
Research sketchbook - Interaction ModuleResearch sketchbook - Interaction Module
Research sketchbook - Interaction Module
 
The english language crystal ball: the past present and future of technology ...
The english language crystal ball: the past present and future of technology ...The english language crystal ball: the past present and future of technology ...
The english language crystal ball: the past present and future of technology ...
 
Telecollaborative Exchange and Intercultural Education
Telecollaborative Exchange and Intercultural EducationTelecollaborative Exchange and Intercultural Education
Telecollaborative Exchange and Intercultural Education
 
NOVA Data Science Meetup 1/19/2017 - Presentation 2
NOVA Data Science Meetup 1/19/2017 - Presentation 2NOVA Data Science Meetup 1/19/2017 - Presentation 2
NOVA Data Science Meetup 1/19/2017 - Presentation 2
 
A REVIEW ON THE PROGRESS OF NATURAL LANGUAGE PROCESSING IN INDIA
A REVIEW ON THE PROGRESS OF NATURAL LANGUAGE PROCESSING IN INDIAA REVIEW ON THE PROGRESS OF NATURAL LANGUAGE PROCESSING IN INDIA
A REVIEW ON THE PROGRESS OF NATURAL LANGUAGE PROCESSING IN INDIA
 
Applied linguístics 1
Applied linguístics 1Applied linguístics 1
Applied linguístics 1
 
Managing Reputation in the Digital Age - Magnus Carter
Managing Reputation in the Digital Age - Magnus CarterManaging Reputation in the Digital Age - Magnus Carter
Managing Reputation in the Digital Age - Magnus Carter
 
The richness of rumours & limitations of facts - stijn aelbers
The richness of rumours & limitations of facts - stijn aelbersThe richness of rumours & limitations of facts - stijn aelbers
The richness of rumours & limitations of facts - stijn aelbers
 
Technology in Language Learning
Technology in Language LearningTechnology in Language Learning
Technology in Language Learning
 
John Hajek conference keynote 2014
John Hajek   conference keynote 2014John Hajek   conference keynote 2014
John Hajek conference keynote 2014
 
Open Education and Open Development – working together
Open Education and Open Development – working togetherOpen Education and Open Development – working together
Open Education and Open Development – working together
 
Fonelex Keynote
Fonelex KeynoteFonelex Keynote
Fonelex Keynote
 
Developing media relationships: sustainable conservation | Small charities co...
Developing media relationships: sustainable conservation | Small charities co...Developing media relationships: sustainable conservation | Small charities co...
Developing media relationships: sustainable conservation | Small charities co...
 
Development Aid Support/Knowledge For Development Without Borders (KFDWB)
Development Aid Support/Knowledge For Development Without Borders (KFDWB)Development Aid Support/Knowledge For Development Without Borders (KFDWB)
Development Aid Support/Knowledge For Development Without Borders (KFDWB)
 
ODowd icc_graz_2017
ODowd icc_graz_2017ODowd icc_graz_2017
ODowd icc_graz_2017
 
Denmark ECML 2016
Denmark ECML 2016Denmark ECML 2016
Denmark ECML 2016
 
Presentation at Kigali Institute of Education - Setember 2009
Presentation at Kigali Institute of Education - Setember 2009Presentation at Kigali Institute of Education - Setember 2009
Presentation at Kigali Institute of Education - Setember 2009
 
Weaving Global Partnerships: Telecollaboration in University Education
Weaving Global Partnerships: Telecollaboration in University EducationWeaving Global Partnerships: Telecollaboration in University Education
Weaving Global Partnerships: Telecollaboration in University Education
 

Plus de Idibon1

Gender, language, and Twitter: Social theory and computational methods
Gender, language, and Twitter: Social theory and computational methodsGender, language, and Twitter: Social theory and computational methods
Gender, language, and Twitter: Social theory and computational methods
Idibon1
 

Plus de Idibon1 (10)

Computing with Affective Lexicons: Computational Linguistics Tutorial with Da...
Computing with Affective Lexicons: Computational Linguistics Tutorial with Da...Computing with Affective Lexicons: Computational Linguistics Tutorial with Da...
Computing with Affective Lexicons: Computational Linguistics Tutorial with Da...
 
Conspiracy, complaints, and fraud: The language of reasons
Conspiracy, complaints, and fraud: The language of reasonsConspiracy, complaints, and fraud: The language of reasons
Conspiracy, complaints, and fraud: The language of reasons
 
Ciara Sanker: Personal epistemology and epistemic learning
Ciara Sanker: Personal epistemology and epistemic learningCiara Sanker: Personal epistemology and epistemic learning
Ciara Sanker: Personal epistemology and epistemic learning
 
Suzanne Wertheim: Linguistic Anthropology meets NLP
Suzanne Wertheim: Linguistic Anthropology meets NLPSuzanne Wertheim: Linguistic Anthropology meets NLP
Suzanne Wertheim: Linguistic Anthropology meets NLP
 
Will Monroe: Text to 3D scene generation with lexical grounding
Will Monroe: Text to 3D scene generation with lexical groundingWill Monroe: Text to 3D scene generation with lexical grounding
Will Monroe: Text to 3D scene generation with lexical grounding
 
Gender, language, and Twitter: Social theory and computational methods
Gender, language, and Twitter: Social theory and computational methodsGender, language, and Twitter: Social theory and computational methods
Gender, language, and Twitter: Social theory and computational methods
 
Counts, comparisons, collocations, contestations: Towards a dictionary of the...
Counts, comparisons, collocations, contestations: Towards a dictionary of the...Counts, comparisons, collocations, contestations: Towards a dictionary of the...
Counts, comparisons, collocations, contestations: Towards a dictionary of the...
 
Pattern recognition and the crowd
Pattern recognition and the crowdPattern recognition and the crowd
Pattern recognition and the crowd
 
Dan Jurafsky: The Language of Food
Dan Jurafsky: The Language of FoodDan Jurafsky: The Language of Food
Dan Jurafsky: The Language of Food
 
Chris Potts: Sentiment analysis in context
Chris Potts: Sentiment analysis in contextChris Potts: Sentiment analysis in context
Chris Potts: Sentiment analysis in context
 

Dernier

Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 

Dernier (20)

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
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
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)
 
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 Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.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
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
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...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
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...
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
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
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
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
 
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...
 

Understanding Community Needs: Scalable SMS Processing for UNICEF Nigeria and Burundi

  • 1. Understanding Community Needs: Scalable SMS Processing for UNICEF Nigeria and Burundi Jessica Long Senior software engineer at Idibon
  • 2. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program, and Idibon’s collaboration • Lessons learned from automatic labeling in English and minority languages • Conclusions
  • 3. Acknowledgements • Robert Munro, CEO of Idibon • Caroline Barebwoha, U-Report Nigeria project lead • Aboubacar Kampo, U-Report Nigeria project lead • Sarah Atkinson, U-Report Burundi project lead • Kidus Fisaha Asfaw, Global head of U-Report • Evan Wheeler, CTO of UNICEF Innovation / RapidPro • Nicholas Gaylord, data scientist at Idibon
  • 4. My background Symbolic Systems BS Computer Science MS Health systems manager in rural Burundi Internationalization engineer Second language acquisition research NLP engineer
  • 5. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program, and Idibon’s collaboration • Lessons learned from automatic labeling in English and minority languages • Conclusions
  • 6. What is Natural Language Processing (NLP)? Natural language processing is a branch of artificial intelligence specifically concerned with making automatic judgments about free text
  • 7. Flavors of NLP • Automatic categorization • Machine translation • Named entity recognition • Sentiment Analysis • Semantic Role Labeling • Opinion Mining • Parsing • Question Answering • Search – 15% of Google’s daily search queries have never been issued before! • Part of Speech Tagging • Textual Entailment • Discourse Analysis • Natural language Generation • Speech Recognition • Word sense disambiguation • Text summarization
  • 8. Underlying algorithms • Semi-supervised machine learning – Start with labeled training data that’s similar to what you want to generate – Use this to “teach” the computer what features to look for when making a decision about the text Cat Cat Cat ??? Dog Dog Dog Training set Predictio n
  • 9. Semi-supervised machine learning example • “Using Wikipedia for Automatic Word Sense Disambiguation,” by Rada Mihalcea (2007) Paris, France Paris, Texas Paris, France Paris, France Paris, Texas
  • 10. Tokenization and feature extraction (n-grams) “tomb”, “of”, “the”, “unknown”, “soldier”, “beneath”, “arc”, “de”, “triomphe” “tomb of”, “of the”, “the unknown”, “unknown soldier”, “beneath the”, “the arc”, “arc de”, “de triomphe” “tomb of the”, “of the unknown”, “the unknown solider”, “unknown soldier beneath”, “beneath the arc”, “the arc de”, “arc de triomphe” Other features - Punctuation - Stemming - Parsing - Capitalization - Dictionary matching - Stopwords - … Paris, France Source text Source label Extracted features
  • 11. Who uses NLP? Apple’s Siri does speech recognition on human voices, as well as question answering IBM Watson answers Jeopardy questions
  • 12. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program, and Idibon’s collaboration • Lessons learned from automatic labeling in English and minority languages • Conclusions
  • 13. Language resources for UNICEF Uganda 30+ Languages Spoken in Uganda Google Translate Supported Languages
  • 14. Why is NLP difficult for minority languages? • Lots of code-switching breaks usual paradigm of language- specific textual analysis • Lack of existing digital tools: spell check, autocomplete, access to internet • Minority language speakers lack purchasing power • Tokenization – Consider: • “ntibazoronka.”: “nta” “i” “ba” “zo” “ronka” “.” (Kirundi) • “they will not obtain.”: “they” “will” “not” obtain” “.” (English) • Encoding issues – “I can text you a pile of poo , but I can’t write my name” by Aditya Mukerjee in Model View Culture
  • 15. But most of all. . . • Minority languages lack appropriate training datasets. – They tend to be primarily spoken, and lack the digital and even written content necessary for statistical machine learning • Google Translate relies on parallel corpora from UN proceedings to help create machine translation products – The UN does not dual broadcast in Wolof. • Textual reviews matched to star ratings on Yelp helps researchers calibrate sentiment analysis – Yelp is literally non-functional in most of Africa.
  • 16. “Raw data is an oxymoron.” - Lisa Gitelman
  • 17. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program, and Idibon’s collaboration • Lessons learned from automatic labeling in English and minority languages • Conclusions
  • 18. Curation of language data, old & new Compiled by Webster Collective wisdom, at scale Compiled by experts, Supplemented by OED Reading Programme * Shout out! Go see Martin Benjamin’s talk on The Kamusi Project tomorrow at 13:45, for more information on dictionary curation
  • 19.
  • 20. Creating new structured data with crowdsourcing • “Are two heads better than one? Crowdsourced translation via a two-step collaboration of non- professional editors and translators”, Yan et al – Creating parallel corpuses with crowd workers is much faster and cheaper than using professional translators • Now, more than ever, we have the ability to rapidly create new labeled language data – …as long as we can find proficient writers of minority languages with digital literacy, electricity, and internet access
  • 21. Cell phone access • Nearly 6 billion people in the world have access to a cell phone • In 2013, the UN famously reported that more people have access to a cell phone than to a toilet
  • 22. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program, and Idibon’s collaboration • Lessons learned from Idibon’s automatic labeling in English and minority languages • Conclusions
  • 23. UNICEF’s U-Report • Crowd wisdom, in real time, in developing countries • In 2012, UNICEF Innovation team started building a real- time SMS polling service for UNICEF Uganda. As of 2015, U- Report operates in over 15 countries • Polls are sent out once a week on topics like: – Has ur community addressed social inclusion issues affecting women, youth, and children? – If you get water from a well, borehole, or community tap, is it working today? – Go to your local health center and tell us: Do they give free HIV / AIDS tests? Report YES or NO and HEALTH CENTER NAME
  • 24. UNICEF’s U-Report • Eventually, UNICEF started receiving urgent, unsolicited messages – FLOOD.villages of X, Y sub.county suffering. • UNICEF Nigeria alone now receives 10,000+ unsolicited messages per day • UNICEF needs a way to: – Identify topically relevant messages to share with specific partners – Prioritize which messages to respond to first • Idibon labels messages with urgency, category label, and language, in real time
  • 25. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program • Lessons learned from Idibon’s automatic labeling in English and minority languages • Conclusions
  • 26. Lesson #1: It’s difficult to predict how many new people will use your product / service when you start supporting a new language Non-English Languages of Nigeria 0 5 10 15 20 25 30
  • 27. Lesson #1: It’s difficult to predict how many new people will use your product / service when you start supporting a new language # unsolicited Hausa messages per day Hausa polls begin * But we don’t see the same effect for Yoruba
  • 28. Lesson #2: Language mixing in an African context has different considerations for classification algorithms vs European language code-switching • Downside: complex tokenization • Upside: radically different word structure
  • 29. Lesson #3: Geopolitical context affects how we interpret short messages, and it’s constantly changing
  • 30. Lesson #4: Mutually exclusive categories are elusive. To automatically label messages is to discover the endless ambiguity in human discourse. - Is a washed out road more related to infrastructure or personal safety? - Is education scoped to a particular time in life? Does post-graduate education count? What about education outside of a scholastic context? - If a town’s full name is “Mbale Village,” is “Mbale” a valid place name? - How specific do messages need to be to constitute a security threat? Does “these days some of our young people are not safe” count?
  • 31. Overview • Who’s involved in this project? • What is Natural Language Processing (NLP)? • What are the challenges of creating NLP for minority languages and multilingual societies? • How has the digital age changed how we curate language data? • UNICEF’s U-Report program, and Idibon’s collaboration • Lessons learned from automatic labeling in English and minority languages • Conclusions
  • 32. Conclusions • Crowdsourcing, machine learning, and the proliferation of cell phones make amazing new communication tools and digital language data possible • Invest in translators and analysts