1. Outline
DysWebxia: A Text Accessibility Model for People with Dyslexia
Ricardo Baeza-Yates
Web Research Group
Universitat Pompeu Fabra
& Yahoo Labs Barcelona
Luz Rello
Advisors:
Horacio Saggion
Natural Language Processing Group
Universitat Pompeu Fabra
Barcelona
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
2. OOuuttlliinnee
— What?
!
— Why?
— Goal
!
— Motivation
— Understanding
— Text Presentation
— Text Content
— How? — Integration
— Methodology
Applications
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
3. MOauintl iGneoal
Improve Digital
Accessibility
People with
Dyslexia
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
4. SecoOnduatlriyn eGoals
— To have a deeper understanding of dyslexia by analyzing how people
with dyslexia read and write, using their misspelling errors as a starting
point.
!
— To find out the best text presentation parameters which benefit the
reading performance –readability and comprehension– of people with
dyslexia.
!
— To find out the text content modifications that benefit the reading
performance of people with dyslexia.
!
— To propose a set of recommendations combining the positive results,
and integrate them in reading applications for people with dyslexia.
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
5. OWuthliyn?e
Dyslexia is a learning
disability characterized by
difficulties with accurate
word recognition and by
poor spelling and decoding
abilities
!
!
!
As side effect, this
impedes the growth of
vocabulary and
background knowledge.
Children with dyslexia
tend to show signs of
depression and low self-esteem
[Vellutino et al., 2004]
[International
Association of
[Shaywitz, 2008] Dyslexia, 2011]
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
6. Dyslexia
Outline
— 8.6% in Spanish (Canary Islands)
— 11.8% in Spanish (Murcia)
— 10 - 17.5% of the USA population
— 10.8% English speaking children
— Neurological origin
— Language specific manifestations
— Most frequent signal
— 15.2% in Europe
— 25% in Spain
— 4 of 6 cases are related to dyslexia
Frequent
!
!
!
!
!
Universal
!
!
!
!
School
Failure
[Jiménez et al. 2009]
[Carrillo et al. 2011]
[National Academy of
Sciences, 1987]
[Shaywitz et al. 1992]
[Vellutino et al., 2004]
[Brunswick, 2010]
[International Dyslexia
Association, 2011]
[European Commission, 2011]
[Eurostat, 2011]
[Spanish Federation of
Dyslexia, 2008]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
7. Dyslexia
Outline
— Information access
— Information democratization
[United Nations Committee of
the General Assembly, 2006]
[McCarthy & Swierenga,
— Benefits people without dyslexia
— Benefits others users, e.g. low vision
— Digital format
— eBook sales increased by
115.8% (January 2011)
Human
Right
!
!
!
!
Good for
Dyslexia,
Useful for All
!
!
!
Right
Moment
[Dixon, 2007]
2010]
[Evett & Brown, 2005]
[Association of American
Publishers, 2011]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
8. A Multidishciopwli?nary Challenge
Cognitive Neuroscience
Which problems
dyslexic people
experience?
Are there
linguistic
foundations?
Linguistics
How can we Eye-tracking
measure the
reading
performance?
How NLP
could help
dyslexic people?
How text
presentation
could help
people with
dyslexia?
Natural Language
Processing
Human
Computer
Interaction
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
9. A Multidishciopwli?nary Challenge
How can we Eye-tracking
measure the
reading
performance?
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
10. How Do WeO Ruetalidn?e Eye Tracking!
Every dot is a fixation point
See VIDEO here: https://www.youtube.com/watch?v=P1dRqpRi4cs
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
11. Methodology - ParOticuitpliannets, Equipment
Participants with Dyslexia Control Group
— From 23 to 56 participants
— Native Spanish speakers
— Confirmed diagnosis of dyslexia
— Ages ranging from 11 to 56
(average around 20 - 21 years depending
on the experiment)
— Participants with attention deficit disorder
— Frequent users of Internet and frequent readers
— Education
— Same number
— Idem
!
— Mapped
!
!
!
!
— Similar
— Similar
Eye-Tracker
!
— Tobii T50 (17-inch TFT monitor)
How people withP dhyDs lTexhieas irse aDde faennds ew —ha t2 7ctahn JHuCnIe a2n0d14 N, LUPn ivdeor saibtaotu tP iotm? p e u F a b r a , B a r Kceelyonnaote at DSAI 2013
12. MethodoOlougtyli n—e Materials
Base Texts
— Same genre
— Similar topics
— Same number of sentences
— Same number of words
— Similar average word length
— Same number of unique named entities,
foreign words and same number/
type of numerical expressions
Text Presentation — Controlled
Comprehension
Questionnaires
— Multiple choice tests
— Literal and inferential questions.
— Correct, partially correct and wrong answers
Text
modifications
(Independent
variables)
muy fácil
‘very easy’
muy difícil
‘very difficult’
1 2 3 4 5
Facilidad de Comprensión
Facilidad comprensión
Subjective Ratings ‘Ease of understanding’
+
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
13. Outline
— within-subjects design
— between-subject design
Eye tracking
Questionnaires
Survey
Methodology — Design
Design
Dependent Variables
Quantitative Data
Qualitative Data
Statistical Tests
(conditions in counterbalanced order)
Likert scales
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
14. OOuuttlliinnee
— What?
!
— Why?
— Goal
!
— Motivation
— Understanding
— Text Presentation
— Text Content
— How? — Applications
— Methodology
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
15. Outline
Understanding
How people withP dhyDs lTexhieas irse aDde faennds ew —ha t2 7ctahn JHuCnIe a2n0d14 N, LUPn ivdeor saibtaotu tP iotm? p e u F a b r a , B a r Kceelyonnaote at DSAI 2013
16. A Multidishciopwli?nary Challenge
Cognitive Neuroscience
Which problems
dyslexic people
experience?
Are there
linguistic
foundations?
Linguistics
How can we Eye-tracking
measure the
reading
performance?
How NLP
could help
dyslexic people?
How text
presentation
could help
people with
dyslexia?
Natural Language
Processing
Human
Computer
Interaction
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
17. A Multidishciopwli?nary Challenge
Cognitive Neuroscience
Which problems
dyslexic people
experience?
Are there
linguistic
foundations?
Linguistics
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
18. WhOyu tElirnreors?
Understanding
Text Presentation
Text Content
Integration
!
Dyslexia
— Studying dyslexia
— Diagnosing dyslexia
— Accessibility tools
!
!
The Web
— Detecting spam
— Measuring quality
Errors
Source of
Knowledge
[Treiman, 1997]
[Lindgrén & Laine, 2011]
[Schulte-Körne et al. 1996]
[Pedler, 2007]
[Piskorski et al. 2008]
[Gelman & Barletta, 2008]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
19. DyslexOiau tinli ntehe Web
Understanding
Text Presentation
Text Content
Integration
[Rello & Baeza-Yates, New Review of Hypermedia and Multimedia, 2012]
English Spanish
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
20. Are there LinOguutislitnice Foundations?
Written Errors by People with Dyslexia
Understanding
Text Presentation
Text Content
Integration
[Rello & Llisterri, LDW 1012 ]
[Rello, Baeza-Yates & Llisterri, LREC 2014]
Analysis
Visual & Phonetic
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
21. How Do We Process Text?
Outline
Understanding
Text Presentation
Text Content
Integration
Please read this text. It is just an example but helps
to underztand how we read text. A text can be
legivle but this does not mean that it will be
compreensible. Hence, we habe to take care about
the presantation of a text as well as the lexical,
syntactic, and semmantical levels of its content.
Test
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
22. Does Lexical Quality Matters?
Outline
Understanding
Text Presentation
Text Content
Integration
Variant B
Variant A
Demographic Questionnaire
Text 1: 16% errors Text 2: 16% errors
Comprehension Test
Error Perception Test
Text 2: 16% errors Text 1: 16% errors
Comprehension Test
Comprehension Test
Comprehension Test
Error Perception Test
Writing/memory test
— 0 or 12/75 words
(16% errors)
— dyslexic
— unique
Errors
priosridad
presupuetsos
indutricas
implse
[Rello & Baeza-Yates, WWW 2012 (poster)]
Error Awareness Dependent Measure
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
23. Results —Ou Ltleixniecal Quality
Understanding
Text Presentation
Text Content
Integration
[Rello & Baeza-Yates, WWW 2012 (poster)]
Group D
no effects!
Group N
(p = 0.08)
ρ = 0.799
(p < 0.001)
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
24. How Fast YOouut lCinaen Read This?
Olny srmat poelpe can raed tihs !
Understanding
Text Presentation
Text Content
Integration
!
I cdnuolt blveiee taht I cluod aulaclty uesdnatnrd
waht I was rdanieg. Due to the phaonmneal pweor of the
hmuan mnid, aoccdrnig to a raerscheer at Cmabrigde
Uinervtisy, it deosn't mttaer in waht oredr the
ltteers in a wrod are, t he olny iprmoatnt tihng is
taht the frist and lsat ltteer are in the rgh it
pclae. The ruslet can be a taotl mses but you can
sitll raed it wouthit a porbelm. Tihs is bcuseae the
huamn mnid deos not raed ervey lteter by istlef, but
the wrod as a wlohe. Amzanig huh? Yaeh and I awlyas
tghuhot taht slpeling was ipmorantt!
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
25. How WellO Wutel iPnerocess Text?
Understanding
Text Presentation
Text Content
Integration
[Baeza-Yates & Rello, to be submitted, 2014]
Words with Errors
Comprehension Score (%)
100.0
87.5
75.0
62.5
50.0
with Errors
No errors 8% errors 16% errors 50% errors
Without Dyslexia
With Dyslexia
Reading Time
also increases
How important is the order in our internal representation of words?
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
26. Do TheyO Suetlei ntehe Errors?
Understanding
Text Presentation
Text Content
Integration
See VIDEO here: https://www.youtube.com/watch?v=P1dRqpRi4cs
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
27. CoOnutrtilbinuetions
Understanding
Text Presentation
Text Content
Integration
— The presence of errors written by people with dyslexia in the text
does not impact the reading performance of people with dyslexia,
while it does for people without dyslexia.
— Normal –correctly written– texts present more difficulties for
people with dyslexia than for people without dyslexia. To the contrary,
texts with jumbled letters present similarly difficulties, for both,
people with and without dyslexia.
— Lexical quality is a good indicator for text readability and
comprehensibility, except for people with dyslexia.
— Written errors by people with dyslexia are phonetically and visually
motivated. The most frequent errors involve the letter without a one-to-one
correspondence between grapheme and phone. Most of the
substitution errors share phonetic features and the letters tend to have
certain visual features, such as mirror and rotation features.
— The rate of dyslexic errors is independent from the rate of spelling
errors in web pages. Around 0.67% and 0.43% of the errors in the Web
are dyslexic errors for English and Spanish, respectively. These rates
are smaller than expected probably due to spelling correction aids.
Rello L., Baeza-Yates R., and
Llisterri, J. DysList: An
Annotated Resource of
Dyslexic Errors. In: Proc.
LREC’14. Reykjavik, Ice-land;
2014. p. 26–31.
Rello L., and Llisterri, J.
There are Phonetic
Patterns in Vowel
Substitution Errors in
Texts Written by Persons
with Dyslexia. In: 21st
Annual World Congress
on Learning Disabilities
(LDW 2012). Oviedo,
Spain; 2012. p. 327–338
Rello L., and Baeza-Yates R.
The Presence of English
and Spanish Dyslexia in
the Web. New Review of
Hypermedia and
Multimedia. 2012;8. p.
131–158
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
28. Outline
Text Presentation
How people withP dhyDs lTexhieas irse aDde faennds ew —ha t2 7ctahn JHuCnIe a2n0d14 N, LUPn ivdeor saibtaotu tP iotm? p e u F a b r a , B a r Kceelyonaote at DSAI 2013
29. A Multidishciopwli?nary Challenge
How can we Eye-tracking
measure the
reading
performance?
How text
presentation
could help
people with
dyslexia?
Human
Computer
Interaction
Cognitive Neuroscience
Which problems
dyslexic people
experience?
Are there
linguistic
foundations?
Linguistics
How NLP
could help
dyslexic people?
Natural Language
Processing
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
30. A Multidishciopwli?nary Challenge
How text
presentation
could help
people with
dyslexia?
Human
Computer
Interaction
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
31. CondOituiotnlisn eStudied
Understanding
Text Presentation
Text Content
Integration
— Font type
— Font size
— Font grey scale & background grey scale
— Color pairs
— Character spacing
— Line spacing
— Paragraph spacing
— Column width
Text Presentation
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
32. WOhyu tFlionnets?
Fonts Designed for Dyslexia
User Studies
What is missing?
!
Evidence via
quantitative
data
!
!
!
Participants
!
!
!
More fonts
Most frequent fonts
Recommendations
The British Dyslexia Association
sans-serif
fonts
— Arial
— no italics
— no fancy fonts
Sylexiad, OpenDyslexic,
Dyslexie & Read Regular
— Arial and Dyslexie
— word-reading test
— 21 students
[De Leeuw, 2010]
[Rello & Baeza-Yates, ASSETS 2013]
What has been done so far?
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
33. MethodOoluotglyin —e Design
Italics
roman
!
italic
Serif
sans serif
!
serif
Spacing
Understanding
Text Presentation
Text Content
Integration
monospace
!
proportional
Independent
variables
[Rello & Baeza-Yates, ASSETS 2013]
Dyslexic
specially designed
!
not specially designed
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
34. Outline
Understanding
Text Presentation
Text Content
Integration
Survey
Methodology — Design
[Rello & Baeza-Yates, ASSETS 2013]
OpenDyslexic Italic
Times
Times Italic
Verdana
[±Italic] [−Italic]
[+Italic]
[± Serif] [−Serif]
[+Serif]
[±Monospace] [−Monospace]
[+Monospace]
[±Dyslexic] [− Dyslexic]
[+ Dyslexic]
Font Experiment
[±Dyslexic It.] [− Dyslexic It.]
Design Within-subjects
Independent Font Type Arial
Variables Arial Italic
[+ Dyslexic It.]
Dependent Reading Time (objective readability)
Variables Fixation Duration
Computer Modern Unicode (CMU)
Courier
Garamond
Helvetica
Myriad
OpenDyslexic
OpenDyslexic Italic
Times
Times Italic
Verdana
Preference Rating (subjective preferences)
Control Variable Comprehension Score (objective comprehensibility)
Participants Group D (48 participants) 22 female, 26 male
Age: range from 11 to 50
(¯x = 20.96, s = 9.98)
Education: high school (26),
university (19),
no higher education (3)
Group N (49 participants) (28 female, 21 male)
age range from 11 to 54
(¯x = 29.20, s = 9.03)
Education: high school (17),
university (27),
no higher education (5)
[±Italic] [−Italic]
[+Italic]
[± Serif] [−Serif]
[+Serif]
[±Monospace] [−Monospace]
Materials Texts 12 story beginnings
[+Monospace]
Text Presentation
Comprehension Quest. 12 literal items (1 item/text)
Preferences Quest. 12 items (1 item/condition)
[±Dyslexic] [− Dyslexic]
[+ Dyslexic]
[±Dyslexic It.] [− Dyslexic It.]
Equipment Eye tracker Tobii 1750
[+ Dyslexic It.]
Procedure Steps: Instructions, demographic questionnaire,
Dependent Reading Time (objective readability)
Variables Fixation Duration
reading task (⇥ 12), comprehension questionnaire (⇥ 12),
preferences questionnaire (⇥ 12)
Preference Rating (subjective preferences)
Control Variable Comprehension Score (objective comprehensibility)
Participants Group D (48 participants) 22 female, 26 male
Age: range from 11 to 50
(¯x = 20.96, s = 9.98)
Education: high school (26),
Table 9.2: Methodological summary for the Font Experiment.
— 12 different texts
— 12 different fonts
(counter-balanced)
Base Texts — comparable
— Same genre
— Same discourse structure
— Same number of sentences: 11
— Same number of words: 60
— Similar word length
(from 4.92 to 5.87 letters)
— No acronyms, foreign words,
or numerical expressions
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
35. Results —O Fuitxlianteion Duration
D group
Fixation Duration: χ2 (11) = 93.63, p < 0.001
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
36. Results —O Fuitxlianteion Duration
D group
Fixation Duration: χ2 (11) = 93.63, p < 0.001
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
37. Results —O Fuitxlianteion Duration
D group
Fixation Duration: χ2 (11) = 93.63, p < 0.001
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
38. Results —O Fuitxlianteion Duration
D group
Fixation Duration: χ2 (11) = 93.63, p < 0.001
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
39. ORuetsliunlets
Understanding
Text Presentation
Text Content
Integration
D group [Rello & Baeza-Yates, ASSETS 2013]
Partial order obtained from Reading Time and Preference Ratings
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
40. Outline
[Rello & Baeza-Yates, ASSETS 2013]
— Font types have an impact on readability of people (with/out dyslexia)
!
— OpenDys and OpenDys It. did not lead to a better or worse read
!
Values with positive e↵ects for
Condition Measures with Dyslexia without Dyslexia
Font Type Obj. Readability Arial Arial
Courier Courier
CMU CMU
Helvetica Verdana
Preferences Verdana Verdana
Helvetica Helvetica
Arial Arial
Recommendation: Arial, Courier, CMU, Helvetica,
and Verdana.
Font Face Obj. Readability roman roman
sans serif sans serif
monospaced monospaced
Preferences roman roman
sans serif no e↵ects
no e↵ects proportional
Recommendation: roman, sans serif and monospaced.
Font Size Obj. Readability 18, 22 and 18, 22 and
26 points 26 points
Obj. Comprehensibility 18, 22 and 14, 18, 22 and
26 points 26 points
Understanding
Text Presentation
Text Content
Integration
Results
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
41. Text PreseOntuattliionne - Conditions
— Font type
— Font size
— Font grey scale & background grey scale
— Color pairs
— Character spacing
— Line spacing
— Paragraph spacing
— Column width
dyslexia dyslexia
dyslexia
dyslexia dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
Understanding
Text Presentation
Text Content
Integration
[Rello, Kanvinde & Baeza-Yates, W4A 2012]
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
black/
white
off-black/
off-white
black/
yellow
blue/
white
dyslexia size:
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
grey scale:
0%
black/
creme
dark brown/
light mucky green
brown/
mucky green
blue/
yellow
25%
50%
75%
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
black/
white
off-black/
off-white
black/
yellow
blue/
white
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
dyslexia
grey scale:
0%
black/
creme
dark brown/
light mucky green
brown/
mucky green
blue/
yellow
char. spacing:
+14%
+7%
0%
–7%
25%
50%
75%
dyslexia
dyslexia
14 p.
18 p.
22 p.
24 p.
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
42. Text PreOseunttlainteion — Web
Understanding
Text Presentation
Text Content
Integration
[Rello, Pielot, Marcos & Carlini, W4A 2013]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
43. CoOnutrtilbinuetions
— Larger font sizes improve the readability,
especially for people with dyslexia.
— Larger character spacing improve readability for
people with and without dyslexia.
— For reading web text, font size of 18 points ensures
good subjective and objective readability and
comprehensibility.
— Sans serif, monospaced, and roman font types
increase the readability of people with and without
dyslexia, while italic fonts decrease it.
— Good fonts for people with dyslexia are Helvetica,
Courier, Arial, Verdana and CMU, taking into
consideration both, reading performance and
subjective preferences.
Understanding
Text Presentation
Text Content
Integration
Rello, L. and Baeza-Yates, R. Good Fonts for
Dyslexia. Proc. ASSETS’13. Bellevue,
Washington, USA: ACM Press; 2013.
Rello & Baeza-Yates, How to Present more
Readable Text for People with Dyslexia.
An eye-tracking study on text colors, size
and spacings. To appear in Universal
Access in the Information Society (UAIS).
Rello, L., Kanvinde, G., Baeza-Yates, R. Layout
guidelines for web text and a web service
to improve accessibility for dyslexics. In:
Proc. W4A 2012. Lyon, France: ACM
Press; 2012.
Rello L., Pielot M., Marcos, MC., and Carlini
R. Size Matters (Spacing not): 18 Points
for a Dyslexic-friendly Wikipedia. In: Proc.
W4A ’13. Rio de Janeiro, Brazil: ACM
Press; 2013.
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
44. Outline
Text Content
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
45. A Multidishciopwli?nary Challenge
How can we Eye-tracking
measure the
reading
performance?
How NLP
could help
dyslexic people?
How text
presentation
could help
people with
dyslexia?
Natural Language
Processing
Cognitive Neuroscience
Which problems
dyslexic people
experience?
Are there
linguistic
foundations?
Linguistics
Human
Computer
Interaction
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
46. A Multidishciopwli?nary Challenge
How NLP
could help
dyslexic people?
Natural Language
Processing
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
47. ProbleOmus tolifn De yslexia
Understanding
Text Presentation
Text Content
Integration
Surface Dyslexia
Orthography
— Orthographically similar words:
homo, horno
— Alternation of different typographical
cases: ElefANte
Phonological
Dyslexia
— Less frequent words: prístino
— Long words: colecciones
— Substitutions of functional words: para, por
— Confusions of small words: en, el, es
Phonology
— Irregular words: vase
— Homophonic words or
pseudo homophonic words
!
— Foreign words
Discourse
— Long
sentences
— Long
paragraphs
Morphology
— Derivational errors: *inmacularidad
Lexicon & Syntax
— New words: chocaviar
— Pseudo–words and non–words: maledo
Cognitive
Neuroscience
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
48. How NOLuPtl icnaen Help?
Difficulties
Orthography & Phonology
Morphology, Lexicon & Syntax
Derivational errors
New words
Pseudo-words
Less frequent words
Long words
Functional words
Small words
Understanding
Text Presentation
Text Content
Integration
Content
Conditions
— Errors
Discourse Visual Thinking
— Graphical
Strong visual thinkers
Pattern Recognition
NLP
Orthographically similar
Misspellings
Irregular words
Homophonic words
Pseudo-homophonic words
Foreign words
Strengths
Orthographic
and Phonetic
Similarity
Measures
Corpus
Analyses
Lexical
Simplification
!
Syntactic
Simplification
— Word frequency
— Word length
— Numerical
Representation
— Paraphrases
Discourse
Simplification
Long sentences
Long paragraphs
Schemes
— Keywords
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
49. Outline
Understanding
Text Presentation
Text Content
Integration
ataques (474 times more freq.)!
!
refriegas
Survey
Methodology — Design
[+FREQUENT]
[−FREQUENT]
[+LONG]
[−LONG]
prestidigitador (3.75 shorter)
!
mago
Word Frequency and Word Length Experiments
Design within-subjects
Word Frequency Experiment
Independent [±Frequent] [+Frequent]
Variables [−Frequent]
Word Length Experiment
[±Long] [+Long]
[−Long]
Dependent Reading Time (Objective readability)
Variables (Sec. 3.1.1) Fixation Duration
Comprehension Score (Objective comprehensibility)
Participants Group D (23 participants) 12 female, 11 male
Age: range from 13 to 37
(¯x = 20.74, s = 8.18)
Education: high school (11),
university (10),
no higher education (2)
Reading: more than 8 hours (13.0%),
4-8 hours (39.1%),
less than 4 hours/day (47.8%)
Group N (23 participants) (13 female, 10 male)
Age: range from 13 to 35
(¯x = 20.91, s = 7.33)
Education: high school (6),
university (16),
no higher education (1)
Reading: more than 8 hours (4.3%),
4-8 hours (52.2%),
less than 4 hours/day (43.5%)
Materials Texts 4 texts (2 texts/experiment)
Synonym Pairs 15 in Word Frequency Exp.
6 in Word Length Exp.
Text Presentation
Compren. Quest. 8 inferential items (2 items/text)
Equipment Eye tracker Tobii 1750
Procedure Steps: (per experiment) Instructions, demographic questionnaire,
reading task (⇥ 2), comprehension questionnaire (⇥ 2), and
preferences questionnaire (⇥ 2)
Table 10.2: Methodological summary for the Word Frequency and
Base Texts — comparable
Target
Words
— common names
— non ambiguous names
— no compound nouns
— no foreign words
— no homophonic words
Frequency
— relative frequencies
(one order of magnitude)
— no short words
Length
— at least double
the length
— longest words
Comprehension
Questionnaires — inferential questions
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
50. Results —O uWtloinred-frequency
90
90
80
80
70
70
60
60
50
50
40
40
30
30
20
20
10
10
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Dempere & Saggion, INTERACT 2013]
Readability axis
−freq +dys
+freq +dys
−freq −dys
+freq −dys
−freq +dys
+freq +dys
−freq −dys
+freq −dys
−freq +dys
+freq +dys
−freq −dys
+freq −dys
Group D: [+Frequent] [–Frequent]
−freq +dys
+freq +dys
−freq −dys
+freq −dys
Group N: [+Frequent] [–Frequent]
Mean fixation duration (s)
Visit duration (s)
−freq +dys
+freq +dys
−freq −dys
+freq −dys
Fixation duration (sec.)
Reading Time (sec.)
0.1 0.15 0.2 0.25 0.3 0.35 0.4
— A larger number of
high frequency words
increases readability
for people with
dyslexia.
!
Reading Time
t(33.488)=−2.120,
p=0.035
Fixation Duration
t(35.741)=−2.150,
p=0.038
— No effects for
Group N
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
51. Outline
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Dempere & Saggion, INTERACT 2013]
Survey
Results — Word-length
— The presence of short
words compared to long words
increases comprehensibility
for people with dyslexia.
!
Comprehension Score
t(38.636) = −2.396, p = 0.022
!
— No effects for Group N
— A total dissociation of frequency and
length is not possible
— Word frequency and word length are
naturally related in language [Jurafsky et al., 2001]
Limitations
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
52. Outline
Survey
Next Steps?
Understanding
Text Presentation
Text Content
Integration
Implement and
evaluate a lexical
simplification
algorithm
Lexical Simplification
Find out how to
make lexical
simplification useful
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
53. What hasO Buetelinn eDone so far?
Experimental psychology
and word processing
Accessibility studies about
people with dyslexia
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Bott & Saggion, W4A 2013 (best paper award)]
What is missing?
Spanish
Word length
Interaction strategies
!
!
!
Automatic
!
!
Natural language processing
and lexical simplification
detect — complex words
(Frequency)
substitute
— dictionaries
— Wordnet
— ontologies
Frequent &
long words
Content
Design
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
54. Evaluation of SimpOliufitclaintieon Strategies
Independent variable
(counter-balanced order)
Lexical simplification
[Rello, Baeza-Yates, Bott & Saggion, W4A 2013 (best paper award)]
ORIGINAL
SUBSBEST
SHOWSYNS
GOLD
laptop
iPad
Android device
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
55. Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Bott & Saggion, W4A 2013 (best paper award)]
— Same genre: Scientific American
— Similar topics: reports from Nature
!
— Same discourse structure
!!!!
— Same number of sentences: 11
— Same number of words: 302
— No acronyms nor numbers
Outline
Survey
Methodology — Design
Lexical Simplification Experiment.
Design Within-subjects
Independent Lexical Simplification [Orig]
Variables Strategy [SubsBest]
[ShowSyns]
[Gold]
Dependent Reading Time (objective readability)
Variables Fixation Duration
Comprehension Score (objective comprehensibility)
Subject. Readability Rating (subjective readability)
Subject. Comprehension Rating (subjective comprehensibility)
Subject. Memorability Rating (subjective memorability)
Participants Group D (47 participants) 28 female, 19 male
Age: range from 13 to 50
(¯x = 24.36, s = 10.19)
Education: high school (18),
university (26), no higher education (3)
Group N (49 participants) (29 female, 20 male)
Age: range from 13 to 40
(¯x = 28.24, s = 7.24)
Education: high school (16),
university (31), no higher education (2)
Materials Base Texts 2 texts
Word Substitutions 34 per text (in [SubsBest]), and
40/44 per text (in [Gold])
Synonyms on-demand 100/110 synonyms for 50/55 words
per text (in [ShowSyns])
Text Presentation
Comprehension Quest. 6 inferential items (3 per text)
Sub. Readability Quest. 2 likert scales (1/condition level)
Sub. Comprehension Quest. 2 likert scales (1/condition level)
Sub. Memorability Quest. 2 likert scales (1/condition level)
Equipment Eye tracker Tobii 1750, Samsung Galaxy Ace S5830
iPad 2, and MacBook Air
Procedure Steps: Instructions, demographic questionnaire, text choosing, reading
task, comprehension questionnaires, sub. readability quest.
sub. comprehension quest., and subjective memorability quest.
Table 14.2: Methodological summary for the Keywords Experiment.
1&2p — Intro
3p — Background
4p — Details
Target Words
Base
Texts
Engagement Choose the text you like!
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
56. Results — ObjeOcutitvlien Me easures
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Bott & Saggion, W4A 2013 (best paper award)]
Group D Group N
No effects!
r = 0.994 r = 0.625 r = 0.429
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
57. Duration Mean Duration Mean ●
Dys.Fixation Duration Mean ●
●
●
0.10 0.15 0.20 0.25 50 100 150 200 [0.10 0.15 0.20 0.25 Font 0.10 0.15 0.20 0.25 Font ●
0.10 0.15 0.20 0.25 Font Results — OSuubtljiencetive Measures
3.294118 3.888889 Original
3.588235 3.700000 LexSIS
4.142857 4.142857 Dyswebxia
3.437500 4.375000 Gold
D Group N
3.647059 4.222222 Original 0.2410992628
3.882353 3.900000 LexSIS
4.285714 4.357143 Dyswebxia
3.625000 4.250000 Gold
Subject. Readability
Group D Group N
3.235294 4.444444 Original -0.084924633
3.647059 3.800000 LexSIS
4.357143 4.285714 Dyswebxia
3.750000 4.250000 Gold
Subject. Comprehension
100 150 200 Fixation 100 150 200 Fixation Understanding
Text Presentation
Text Content
Integration
Dys.Gold Dys.lesSIS 50 H(3) = 9.595, p = 0.022
[SubsBest] more difficult than [Original]
(p = 0.003) and [ShowSyns] (p = 0.047)
H(3) = 9.020, p = 0.029
[SubsBest] significantly more difficult
than [Gold] (p = 0.003)
Group D Group N
Subject. Comprehension
Subject. Memorability
●
●
●
Dys.Gold Dys.lesSIS Dys.lexSIS Dys.Original
Size
Fixation Duration Mean ●
●
●
Dys.Gold Dys.lesSIS Dys.lexSIS Dys.Original
Size
Fixation Duration Mean ●
●
●
Dys.Gold Dys.lesSIS Dys.lexSIS Dys.Original
Size
Dys.Gold Dys.50 100 150 200 Fixation Gold 50 Duration Mean Group D Group N
3.294118 3.888889 Original 0.1597582109
3.588235 3.700000 LexSIS
4.142857 4.142857 Dyswebxia
3.437500 4.375000 Gold
Readability
1 2 3 4 5
Group D Group N
Understandability
1 2 3 4 5
Group D Group N
(ave.) (ave.)
Very bad Very good Very bad Very good
[Original]
[SubsBest]
[ShowSyns]
[Gold]
Memorability
1 2 3 4 5
Very bad Very good
Group D Group N
(ave.)
[Original]
[SubsBest]
[ShowSyns]
[Gold]
[Original]
[SubsBest]
[ShowSyns]
[Gold]
[Gold] [SubsBest] [Original]
Gold] Group D Group N
H(3) = 8.275, p = 0.041
[ShowSyns] easier than [Gold]
(p = 0.034) and [Original] (p = 0.034)
H(3) = 12.197, p = 0.007
[ShowSyns] easier than [SubsBest]
(p = 0.013) and [Original] (p = 0.001)
[Rello, Baeza-Yates, Bott & Saggion, W4A 2013 (best paper award)]
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
58. Understanding
Text Presentation
Text Content
Integration
ORuetsliunlets
[Rello, Baeza-Yates, Bott & Saggion, W4A 2013 (best paper award)]
Lexical
Simplification
substitution negatively
affects the reading experience
does not help
objective
readability
comprehension
subjective measures
interaction matters
showing synonyms on-demand makes
texts more comprehensible and
more readable
help to get out of the vicious circle
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
59. Outline
Understanding
Text Presentation
Text Content
Integration
Survey
Next Steps?
Lexical Simplification
implement and evaluate a
lexical simplification
algorithm
via synonyms on
demand is helpful
language resource of synonyms
available to be used in tools
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
60. What has Been Done so far?
Outline
Resources for Lexical Simplification What is missing?
in Spanish
resource containing lists
of synonyms ranked by
their complexity
— no Simple Wikipedia in Spanish
!
— Simplext Corpus (200 news articles)
6,595 words original and 3,912 words
simplified
!
— Spanish OpenThesaurus (SpOT)
21,378 target words (lemmas),
44,348 different word senses
!
— EuroWordNet
50,526 word meanings, 23,370 synsets
Understanding
Text Presentation
Text Content
Integration
[Baeza-Yates, Rello & Dembowski, to be submitted]
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
61. CASSA
Outline
Input:
Context Aware Synonym Simplification Algorithm
[Baeza-Yates, Rello & Dembowski, to be submitted]
— Google Books N-gram Corpus (5-grams) in Spanish
(8,116,746 books, over 6% of all books, 83,967,471,303 tokens
Understanding
Text Presentation
Text Content
Integration
Output:
— CASSA Resource
Simpler Synonyms
Ranking
Relative Web Frequency
+
Dyslexia
Features
— Analysis of Corpus
of dyslexic errors
Word
Candidates
Complexity
Detection
Relative Web Frequency
Lemmatization
+
Filters
— Valid words
— Proper names
— Stop words
— List of Senses
(from Spanish
OpenThesaurus)
— Web Frequencies
Word Sense
Disambiguation
Context Frequency
— List of Senses
— Google Books
n-gram Corpus
Context Frequencies
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
62. CASSA
Outline
Synonyms Resource for Spanish
CASSA disambiguated
CASSA baseline (Frequency)
Understanding
Text Presentation
Text Content
Integration
[Baeza-Yates, Rello & Dembowski, to be submitted]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
63. Outline
Understanding
Text Presentation
Text Content
Integration
Survey
Methodology — Design
[Rello & Baeza-Yates, W4A 2014
(best paper award runner-up)]
Evaluation Dataset
— 80 target words
HIGH freq.
LOW freq.
— Contexts and sentences
(20th, 21st Century books)
vs. 130 [Biran et al. 2011] and
200 [Yatskar et al. 2010]
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
64. Outline
Understanding
Text Presentation
Text Content
Integration
[Rello & Baeza-Yates, W4A 2014 (best paper award runner-up)]
— Test well calibrated: expected low value answers: 1.41 (s = 0.98) for group D, 1.47 (s = 0.51) for Group N
expected high value answers: 8.77 (s = 0.93) for group D, 9.16 (s = 0.69) for Group N
Survey
Results
— Synonymy & Simplicity
— Ratings of Group N significantly higher than Group G
for all the conditions
!
— Low frequency: better results for all ratings and
conditions
!
— CASSA: More accurate and simpler synonyms
Synonymy Rating (groups D & N)
(H(1) = 110.36, p < 0.001), (H(1) = 198.72, p < 0.001)
Simplicity Rating (groups D & N)
(H(1) = 131.76, p < 0.001), (H(1) = 179.82, p < 0.001)
— New algorithm CASSA, outperforms the
hard-to-beat Frequency Baseline [Specia et al. 2012]
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
65. Conditions Studied
Outline
— Word frequency
— Word length
— Numerical Representation
— Paraphrases
— Graphical Schemes
— Keywords
Text Content
Understanding
Text Presentation
Text Content
Integration
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
66. CoOnutrtilbinuetions
— Frequent words improve readability while
shorter words may improve comprehensibility,
especially in people with dyslexia.
— Numbers represented as digits instead of words, as
well as percentages instead of fractions, improve
readability of people with dyslexia.
— Graphical schemes improve the subjective
readability and comprehensibility of people with
dyslexia.
— Highlighted keywords increases the objective
comprehension by people with dyslexia, but not the
readability.
— Lexical simplification via automatic substitution of
complex words by simpler synonyms is not helpful.
However, showing synonyms on demand improves
the subjective readability and comprehensibility of
people with dyslexia.
Understanding
Text Presentation
Text Content
Integration
Rello, L., Baeza-Yates, R., Dempere, L. and
Saggion, H. Frequent Words Improve
Readability and Short Words Improve
Understand- ability for People with Dyslexia.
Proc. INTERACT ’13. Cape Town, South
Africa: IFIP Press; 2013, p. 203–219
Rello, L., Bautista, S., Baeza-Yates, R., Gervás, P.,
Hervás, R. and Saggion, H. One Half or 50%?
An Eye-Tracking Study of Number
Representation Readability. Proc.
INTERACT ’13. Cape Town, South Africa:
IFIP Press; 2013, p. 229-245
Rello, L., Baeza-Yates, R., Bott, S. and Saggion,
H. Simplify or Help? Text Simplification
Strategies for People with Dyslexia. Proc.
W4A ’13. Rio de Janeiro, Brazil: ACM Press;
2013 (best paper award).
Rello, L. and Baeza-Yates, R. Evaluation of
DysWebxia: A Reading App Designed for
People with Dyslexia. Proc. W4A ’14. Seoul,
South Korea: ACM Press; 2014 (Chapter 15
[319], best paper nominee).
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
67. Outline
Integrating
Form and Content
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
68. Text Presentation
Recommendations
Outline
Understanding
Text Presentation
Text Content
Integration
[Rello & Baeza-Yates, to appear in Universal Access in the Information Society (UAIS)]
Values with positive e↵ects for
Condition Measures with Dyslexia without Dyslexia
Font Type Obj. Readability Arial Arial
Courier Courier
CMU CMU
Helvetica Verdana
Preferences Verdana Verdana
Helvetica Helvetica
Arial Arial
Recommendation: Arial, Courier, CMU, Helvetica,
and Verdana.
Font Face Obj. Readability roman roman
sans serif sans serif
monospaced monospaced
Preferences roman roman
sans serif no e↵ects
no e↵ects proportional
Recommendation: roman, sans serif and monospaced.
Font Size Obj. Readability 18, 22 and 18, 22 and
26 points 26 points
Obj. Comprehensibility 18, 22 and 14, 18, 22 and
26 points 26 points
Subj. Readability 18 and 22 points 18 and 22 points
Subj. Comprehensibility 18, 22 and 14, 18, 22 and
26 points 26 points
Recommendation: 18 and 22 points
Character Spacing Obj. Readability +7%, +14% +7%, +14%
Preferences no e↵ects 0%
Recommendation: ranging from 0 to +14%
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
69. Text Presentation
Recommendations
Outline
Understanding
Text Presentation
Text Content
Integration
[Rello & Baeza-Yates, to appear in Universal Access in the Information Society (UAIS)]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
70. Text Content
Recommendations
Outline
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Dempere & Saggion, INTERACT 2013]
[Rello, Bautista, Baeza-Yates, Gervás, Hervás & Saggion, INTERACT 2013]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
71. Text Content
Recommendations
Outline
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates & Saggion. CICLing 2013]
[Rello, Saggion & Baeza-Yates, PITR 2014]
[Rello, Baeza-Yates, Saggion & Graells, PITR 2012]
[Rello, Baeza-Yates, Bott, & Saggion, W4A 2013]
[Rello, L. and Baeza-Yates. W4A 2014]
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
72. Applhiocawt?ions
IDEAL
e-Book reader
Understanding
Text Presentation
Text Content
Integration
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
73. IDEALO ueBtloinoek Reader
[Kanvinde, Rello & Baeza-Yates, ASSETS 2012 (demo)]
— 35,000 downloads
— Finalist - Vodafone Foundation Smart
Accessibility Awards 2012
Google Play
https://play.google.com/store/apps/
details?id=org.easyaccess.epubreader
Accessible Systems — Usability Evaluation - 14 participants
Mumbai, India
— Table of contents
— Supports text-to-speech technology.
— Spells word-by-word or letter-by-letter.
— Write a comment.
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
d) Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
74. ‘Simpler’
Configuration
Ideal
Font
Color
Synonyms
Helvetica
iOS Reader
Outline
[Rello, Baeza-Yates, Saggion, Bayarri & Barbosa, ASSETS 2013 (demo)]
Soon in the App Store — Usability evaluation with
12 participants
Understanding
Text Presentation
Text Content
Integration
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
75. Text4Oalul tDlinyesWebxia
Understanding
Text Presentation
Text Content
Integration
[Rello, Baeza-Yates, Bott, Saggion, Carlini, Bayarri, Gorriz, Kanvinde, Gupta, Topac 2013 (challenge)]
[Topac 2014 (PhD thesis)]
http://www.text4all.net/dyswebxia.html
by Vasile Topac
Polytechnic University of Timisoara, Romania
— Finalist in The Paciello Group Web
Accessibility Challenge
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
76. Tools Overview
Understanding
Text Presentation
Text Content
Integration
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
77. OnOgouitnlign eWork
Understanding
Text Presentation
Text Content
Integration
— Departament d’Ensenyament
(Àrea de Tecnologies per a l'Aprenentatge i el Coneixement)
Department of Education (Technologies for Learning)
!
!
!
— Cloud4All Project with Technosite
!
!
— Web standards
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
78. Main OCuotnlitnreibutions
— Written errors
— Processed differently (reading) by people with and without dyslexia
— Phonetically and visually motivated
!
— A new model called DysWebxia,
that combines all our results and that
has been integrated so far in four
reading tools.
!
!
— Two new available language resources
http://www.luzrello.com/Resources
— Text Content Recommendations
— Text Presentation Recommendations
— DysList, a list of dyslexic errors
annotated with linguistic, phonetic and
visual features.
!
— CASSA List, a new resource for Spanish
lexical simplification composed of a list of
disambiguated complex words, their
context, and their corresponding simpler
synonyms, ranked by complexity.
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
79. AcknOouwtlleindegments
Ricardo Baeza-Yates
Horacio Saggion
Gaurang Kanvinde
Vasile Topac
Joaquim Llisterri
Mari-Carmen Marcos
Laura Dempere
Simone Barbosa
Clara Bayarri
Stefan Bott
Roberto Carlini
Families with children with dyslexia
People with dyslexia
Yolanda Otal de la Torre
María Sanz-Pastor Moreno de Alborán
Luis Miret
Martin Pielot
Julia Dembowski
Eduardo Graells
Diego Saez-Trumper
Azuki Gorriz
Verónica Moreno
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona
80. Thank you
luzrello@acm.org
How people with dyslexia read and what can HCI and NLP do about it? Keynote at DSAI 2013
PhD Thesis Defense — 27th June 2014, Universitat Pompeu Fabra, Barcelona