Katrien Beuls
VUB Artificial Intelligence Laboratory
State-of-the-art language learning
systems promise “immersive learning”
Rosetta Stone
“Don’t learn a language, absorb it”
“Language learning should be natural”
Terminology of learning theories
(Acquisition-learning distinction, Natural approach)
But they fail to accommodate
for individual student di
ff
erences
Input is not very interesting
- matching activities
- elimination
Every student follows same path irrespective of his answers
Similar to programmed instruction
of the early days of ITS
Krashen, S. (2013). Rosetta Stone: Does not provide compelling input, research reports at best suggestive, conflicting
Academic initiatives try to counter
this lack of individualization
German Tutor (Heift & Schulze, 2007)
- web-based German exercises
- linguistic analysis for feedback
TAGARELA (Amaral & Meurers, 2007)
- web-based language tutoring system
for Portuguese
I propose an
active
student model
That can predict a student’s answers
by simulating the learning task
It is implemented as a student agent
that can process and learn
A constructionist approach
to student modelling
1. Design of an agent-based language tutor
2. Operationalizing processing and learning
A constructionist approach
to student modelling
1. Design of an agent-based language tutor
A competent language user
A student model
A language agent simulates
a competent language user
A construction inventory (grammar)
An engine to process constructions
Flexibility strategies
to flexibly process the target language
A student agent
has the same architecture
Instead of flexibility strategies,
the agent makes use of
learning strategies that target
specific acquisition problems
Also interacts with language agent (no real student required)
language agent
Tutoring strategies mediate
the tutor-student interaction
tutor agent
tutoring language agent
The tutor agent’s student model
consists of a dual structure
A runnable student agent
- predict student’s answers
- align to student every interaction
A more static student profile
- store user profile, preferences
A constructionist approach
to student modelling
2. Operationalizing processing and learning
Fluid Construction Grammar (FCG)
Spanish verb conjugation
FCG lends itself well
for tutoring purposes
Construction-grammar formalism
Everything is a construction
(phon, morph, lex, phrasal, pragmatic)
A construction consists of features
Unification-based (HPSG) but less strict
Customizable search process
The formalism is informative
about failed constructional matches
Processing problems can be detected when parsing student input
Uninterrupted processing guaranteed with meta-level architecture
initial jugar
ía-past-imperfect-2/3
Language agent is initialized with
600 most common verbs in Spanish
18 x 6 conjugated forms / verb
+ 2 imperatives
+ 2 gerunds
= 112 forms / verb
Fred Jehle’s database contains
> 11 000 conjugated verb forms
Pro
fi
ciency evaluated on
learner errors from SPLOCC II corpus
“The emergence and development of the tense-aspect system in L2 Spanish”
408 errors made by
low intermediate learners
- *cogue ➔ coge, ‘he takes’
- *leó ➔ leyó, ‘he read’
- *escuchían ➔ escuchaban, ‘they heard’
SPLOCC results
!
verb class
stem change
unknown suffix
suffix change
unknown stem
43%
stem change
suffix change verb class
unknown stem
The student agent is initialized
with an empty grammar
cxn language agent
cxn student agent
Empty construction inventory
Default grammar engine settings
Learning strategies tackle
learning problems instead of
processing problems
diagnostics
D1 problem-a
Three types of learning strategies
Learning the basics
- unknown stem, suffix
- irregular verb
- new grammatical meaning
Learning verb stem/suffix changes
- coje < coger; pienso < pensar; ...
Learning happens in
discriminative contexts
The student agent can be
the speaker or the hearer in a game
t select
topic
parse consolidate
find student agent
cxn language agent
1 1,2,3
1
2
3
situation situation
produce
1
parse produce give
feedback consolidate
1,2,3
game n+2 select
Example: Three picking events
Student agent:
- topic: event 2
- utterance: “ha recojado”
Language agent:
- correction: “ha recogido”
Student agent learns verb class
now
t
Most learned constructions are su
ffi
xes
lex suffix irreg aux gram
n
A constructionist approach
to student modelling
3. Ideas about tutoring
The Colour Tutoring Game
First tutoring game prototype
for colour word learning
Web interface with colour chips
User can be student or tutor
(teach the system a colour lexicon)
New colour lexicon can be used for future students
Beuls, K., & Bleys, J. (2011). Game-based Language Tutoring. In B. Knox (Ed.) Proceedings of the IJCAI 2011 Workshop
The colour tutoring game
is lacking tutoring strategies
Tutoring strategies serve two functions
1. Selecting a new situation
2. Providing constructive feedback
Spanish verb tutor should tackle
Alignment is critical
for a predictive student model
The tutor agent needs to align
the linguistic knowledge of the student
with the constructions known by the
The language agent and the student
agent form the
basic foundations
for an
adaptive
tutoring system for language
Using
Construction Grammar
to
represent linguistic knowledge is
bene
fi
cial for
understanding
the
Work in progress...
-
Building a
user interface
-
Developing
tutoring strategies
and a data structure they work on
Possible future extensions lead to
-
other game scenarios
-
larger sentences
Further reading
Beuls, K. (2012). Grammatical error diagnosis in Fluid Construction Grammar: A case study in L2 Spanish
verb morphology. Computer Assisted Language
Learning. doi:10.1080/09588221.2012.724426.
Beuls, K. (2012). Inflectional patterns as constructions:
Spanish verb morphology in Fluid Construction
Gammar. Constructions and Frames, 4(2). p 231-252.
Steels, L. (Ed.). (2011). Design Patterns in Fluid
Flexibility strategies
are active during linguistic processing
D1 problem-a R1
D4
problem-c R3
Constructions
relate meaning to form
via
semantic and syntactic
categorizations
meaning
form
semantic
categorizations
syntactic
Detect feature mismatch
Second merge fails due to
different verb class feature in stem
ía = 2/3; jugar = 1
Diagnostic returns verb class feature and its correct value
initial jugar
ía-past-imperfect-2/3
Detect unknown stem
Very frequent problem with beginning learners
juqaba => jugaba
Repaired with closest match on stems in grammar
Levenshtein distance with additional
Learning problem priority list
Front
LP1 LP2 LP3 LP4 LP5 LP6 LP7
Back
Front
LP8 LP3 LP2 LP4 LP5 LP6 LP7