Transcript onr04 - University of Pittsburgh

Spoken Dialogue in Human and
Computer Tutoring
Diane Litman
Learning Research and Development Center
and
Computer Science Department
University of Pittsburgh
Outline
Introduction and Background
 The ITSPOKE System and Corpora
 A Study of Spoken versus Typed Dialogue Tutoring

– Human tutoring condition
– Computer tutoring condition

Current Directions and Summary
Adding Spoken Language to a
Text-Based Dialogue Tutor (11/03-9/06)
 Primary
Research Question
– How does speech-based dialogue interaction impact
the effectiveness of tutoring systems for student
learning?
Hypotheses
 Compared
to typed dialogues, spoken
interactions will yield better learning gains, and
will be more efficient and natural
 Different student behaviors will correlate with
learning in spoken versus typed dialogues, and
will be elicited by different tutor actions
 Findings in human-human and human-computer
dialogues will vary as a function of system
performance
Motivation
 Working
hypothesis regarding learning gains
– Human Dialogue > Computer Dialogue > Text
 Most
human tutoring involves face-to-face
spoken interaction, while most computer
dialogue tutors are text-based
– Evens et al., 2001; Zinn et al., 2002; Vanlehn et
al., 2002; Aleven et al., 2001
 Can
the effectiveness of dialogue tutorial
systems be further increased by using spoken
interactions?
Spoken Tutorial Dialogue Systems
Recent
tutoring systems have begun to add
spoken language capabilities
– Rickel and Johnson, 2000; Graesser et al. 2001;
Mostow and Aist, 2001; Aist et al., 2003; Fry et al.,
2001; Schultz et al., 2003
However,
little empirical analysis of the
learning ramifications of using speech
Potential Benefits of Speech
 Self-explanation
correlates with learning and occurs
more in speech
– Hausmann and Chi, 2002
 Speech
contains prosodic information, providing
new sources of information for dialogue adaptation
– Forbes-Riley and Litman, 2004
 Spoken
computational environments may prime a
more social interpretation that enhances learning
– Moreno et al., 2001; Graesser et al., 2003
 Potential
for hands-free interaction
Spoken Computer Tutoring Excerpt
Tutor: What will the velocity of the object be a second after that
(where the initial velocity is 9.8m/s the acceleration is 9.8m/s^2)?
Student: thirty nine point two
Tutor: Well... 19.6 m/s. So at every point in time during the fall
of the man and his keys, how do their velocities compare with
each other?
Student: same
Tutor: Yeah. Now we will compare the displacements of the
man and his keys. Do you recall what displacement means?
Student: distance in a straight line
Outline
Introduction and Background
 The ITSPOKE System and Corpora
 A Study of Spoken versus Typed Dialogue Tutoring

– Human tutoring condition
– Computer tutoring condition

Current Directions and Summary
ITSPOKE:
Intelligent Tutoring SPOKEn Dialogue System
 Back-end
is text-based Why2-Atlas tutorial dialogue
system (VanLehn et al., 2002)

Student speech digitized from microphone input;
Sphinx2 speech recognizer

Tutor speech played via headphones/speakers; Cepstral
text-to-speech synthesizer
 Other
additions: XML access to Why2-Atlas
“internals”, speech recognition repairs, etc.
Architecture
www
server
html
essay
ITSpoke
java
Why2
xml
Text Manager
www
browser
student
text
(xml)
Essay Analysis
essay
text
Speech
Analysis
dialogue
tutorial
goals
(Sphinx)
repair
goals
dialogue
(Carmel, Tacituslite+)
text
Cepstral
Spoken
Dialogue
Manager
dialogue
tutor turn
(xml)
Content
Dialogue
Manager (Ape,
Carmel)
Speech Recognition: Sphinx2 (CMU)
 56
dialogue-based, probabilistic language models
 Initial training data
– typed student utterances from Why2-Atlas corpora
– human-human: 968 unique words
– human-computer: 599 unique words
 Later
training data
– spoken utterances obtained during development and pilot
testing of ITSPOKE
– human-computer: 523 unique words
 Total
vocabulary
– 1240 unique words
Language Models (LMs): Design
Dialogue-dependent language models manually constructed by aggregating
prompts, e.g. example LM for prompts taking “yes/no” type answers
prompt: Just as the car starts moving, the string is vertical, so it can't exert any horizontal
force on the dice. No other objects are touching the dice. So are there any horizontal
forces on the dice as the car starts moving?
User response
“no”
“none”
“yeah”
“yes”
Count
20
1
1
2
Frequency
83.33
4.17
4.17
8.33
prompt: When analyzing the motion of the two cars, one towing the other, can we treat them
as a single compound body?
User Response
Count
Frequency
“no”
2
8.70
“yes”
21
91.30
Language Models: Evaluation
 Test
Data: ITSPOKE 2003-2004 evaluation
– 20 students, 100 physics problems (dialogues), 2445
turns, 398 unique words
– 39 of 56 language models
•
17 models were either specific to 5 unused physics problems,
or to specific goals that were never accessed
 Word
Error Rate = 31.2%
 “Concept Error” Rate = 7.6%
Speech Synthesis: Cepstral
 Commercial
outgrowth of Festival text-tospeech synthesizer (Edinburgh, CMU)
 Required
additional processing of Why2-Atlas
prompts (e.g., f=m*a)
Spoken Tutoring Corpora
 Human-Human
Corpus
– 14 students, 128 physics problems (dialogues)
– Student and tutor turns were manually transcribed and
segmented for content and boundaries
 Computer-Human
Corpus
– 20 students, 100 physics problems (dialogues)
– Noisy student turn boundaries and transcriptions
extractable from ITSPOKE logs
– Content of student turns also manually transcribed
Corpus Transcription & Annotation
ITSPOKE Corpora Comparison
Human-Human
Human-Computer
…1.3 minutes into session…
…3.5 minutes into session…
Student: Can I ask you questions?
Tutor: I didn't understand. What force acts on all objects within close proximity
to earth?
Tutor: Yes
Student: uh the force of gravity
Student: Is that ok?
Tutor: Fine. Besides the Earth's gravitational force, are there any other forces
acting on the person, keys, and elevator after the release?
Tutor: Mm-hm
Student: Um from what we learned from the last problem
they're gonna have the same- the keys and you have
the same acceleration right?
Tutor: Yes
Student: So that means they'll both hit the bottom at the
same time. But I don't understand where- I don't
understand if you're in the elevatorTutor: You see
Student: Where are you going to-?
Tutor: The uh let me uh the key uh- the person holds the
key in front ofStudent: Their face yeahTutor: Uh his or her face and then lets it uh uh it is let go so
the the the question relates to the relative position of
the key and the face uh-
Student: no
Tutor: Yep. Thus, keep in mind that after the release, the only force on the
person, keys, and elevator is the force of gravity. If gravity is the only force
acting on an object, will it be moving or staying still?
Student: it will be moving
Tutor: Fine. Not only are the person, keys, and elevator moving, they have only
gravitational forces on them. When an object is falling and has only gravitational
force on it, it is said to be in what?
Student: freefall
Tutor: Good. Thus, after the release the only force on the keys and man is the
downward force of earth's gravity, so they are in freefall. Before the release, what
is the relationship between the man's velocity and the keys' velocity?“
Student: they're equal
Tutor: Uh how will they- as they go- as they both fall what
will be their relative position? That is the question.
Tutor: Correct. We know that after the release, the keys, the person, and the
elevator are in freefall. Is freefall acceleration near earth a constant? Or does it
vary depending upon which object is in freefall?“
Student: (sigh)
Student: it's a constant
Student: So the key and the face-
Outline
Introduction and Background
 The ITSPOKE System and Corpora
 A Study of Spoken versus Typed Dialogue Tutoring

– Human tutoring condition
– Computer tutoring condition

Current Directions and Summary
Empirical Results
Spoken Versus Typed Human and Computer
Dialogue Tutoring
Diane Litman, Carolyn Penstein Rosé, Kate Forbes-Riley,
Kurt VanLehn, Dumisizwe Bhembe, and Scott Silliman
Proceedings of the Seventh International Conference on
Intelligent Tutoring Systems (to appear)
Overview
 Given
the effort to develop a spoken tutorial
system, it is important to investigate whether and
how the use of speech can improve student
learning
– by determining the aspects of dialogue that correlate
with learning, we can construct our systems to better
elicit such behaviors
 Two
experiments: spoken versus typed dialogues
– Human tutoring – an upper bound on speech and
natural language processing
– Computer tutoring – current state of the art
Common Aspects of Both Experiments
 Students
take a physics pretest
 Students read background material
 Students use web interface to work through up to
10 problems with either a computer or a human
tutor
 Students take a posttest
– 40 multiple choice questions, isomorphic to pretest
Human Tutoring: Experiment 1
 Same
human tutor, subject pool, physics problems, web
interface, and experimental procedure across two conditions
 Typed dialogue condition (20 students, 171 dialogues)
– Student and tutor in separate rooms
– Strict turn-taking enforced
– Student and tutor type via chat interface
 Spoken
–
–
–
–
dialogue condition (14 students, 128 dialogues)
Student and tutor in same room, separated by a partition
Interruptions and overlapping speech permitted
Student and tutor speak through head-mounted microphones
Dialogue history box remains empty
Typed Excerpt
Spoken Excerpt
(Human Tutoring Corpora)
Problem: Suppose that you released 3 identical balls of clay in a
vacuum at exactly the same instant. They would all hit the
ground at the same instant. Now you stick two of the balls
together, forming one ball that is twice as heavy as the
remaining, untouched clay ball. Both balls are released in a
vacuum at exactly the same instant. Which ball hits the ground
first?
Original Essay: Both balls will hit the ground at the same time. The
balls are in free fall (only gravitational forces). The ratio of the
masses and weight are equal.
--------------------------2 min into dialogue-------------------------------Tutor: You have correctly said the balls are in free fall. What do
you conclude from this fact?
Student: There is no air resistance and the balls’ accelerations are
constant in regards to one another
Problem: If a car is able to accelerate at 2 m/s2, what acceleration
can it attain if it is towing another car of equal mass?
Original Essay: If the car is towing another car of equal mass, the
maximum acceleration would be the same because the car would be
towed behind and the friction caused would only be by the front of
the first car.
-----------------------------6.5 min into dialogue-------------------------Tutor: Now this law that force is equal to mass times acceleration,
what's this law called? This is uh since this it is a very important
basic uh fact uh it is it is a law of physics. Um you have you have
read it in the background material. Can you recall it?
Student: Um no it was one of Newton's laws but I don't- remember
which one. (laugh)
Tutor: Right, right- That- is Newton's second law of motion.
Tutor: Right, so the conclusion is that they both have the same
acceleration, the free fall acceleration. Now you have to show
that time taken by them to reach the ground will be the same.
How do you do that?
Student: he I- Ok, because I remember one, two, and three, but I
didn't know if there was a different name
Student: F (net forces) / mass = f/m because F = m*a therefore ratio
should equal one another
Student: (laugh)
Tutor: But that does not tell you anything about the time taken.
What physical quantities will determine the time taken. Will
the initial velocity of the balls matter?
Student: yes, assuming starting at rest? sorry, kind of at a loss at the
moment
Tutor: Yeah that's right you know Newton was a genius-
Tutor: and uh he looked at a large number of experiments and
experimental data that was available and from that he could come
to this general law and it is known as Newton's second law of
motion. Um many many other scientists before him had seen all this
data which was collected by scientists but had not concluded this
now it looks very simple but to come to the conclusion from a mass
of data was something which required the genius of Newton.
Student: mm hm
Typed versus Spoken Tutoring:
Overview of Analyses
 Tutoring
and Dialogue Evaluation Measures
– learning gains
– efficiency
 Correlation
of Dialogue Characteristics and Learning
– do dialogue aspects differ across conditions?
– which dialogue aspects correlate with learning in each
condition?
Learning and Training Time
Dependent
Measure
Human
Human
Spoken (14) Typed (20)
Pretest Mean (std dev.)
.42 (.10)
.46 (.09)
Posttest Mean (std dev.)
.72 (.11)
.67 (.13)
Adj. Posttest Mean (std dev.)
.74 (.11)
.66 (.11)
Dialogue Time
(std dev.)
166.58
(45.06)
430.05
(159.65)
Discussion
 There
was a robust main effect for test phase
(p=0.000), indicating that students in both conditions
learned during tutoring
 The adjusted posttest scores show a strong trend of
being reliably different (p=0.053), suggesting that
students learned more in the spoken condition
 Students in the spoken condition completed their
tutoring in less than half the time than in the typed
condition (p=0.000)
Dialogue Characteristics Examined
 Motivated
by previous work suggesting that
learning correlates with increased student
language production and interactivity (Core et al.,
2003; Rose et al., pilot studies of typed corpora;
Katz et al., 2003)
– Average length of turns (in words)
– Total number of words and turns
– Initial values and rate of change
– Ratios of student and tutor words and turns
– Interruption behavior (in speech)
Human Tutoring Dialogue
Characteristics (means)
Dependent Measure
Spoken
Typed
(14)
(20)
Tot. Stud. Words
Tot. Stud. Turns
Ave. Stud. Words/Turn
Slope: Stud. Words/Turn
Intercept: Stud. Words/Turn
Tot. Tut. Words
Tot. Tut. Turns
Ave. Tut. Words/Turn
Stud-Tut Tot. Words Ratio
Stud-Tut Words/Turn Ratio
2322.43
424.86
5.21
-.01
6.51
8648.29
393.21
23.04
.27
.25
1569.30
109.30
14.45
-.05
16.39
3366.30
122.90
28.23
.45
.51
p
.03
.00
.00
.04
.00
.00
.00
.01
.00
.00
Discussion
 For
every measure examined, the means across
conditions are significantly different
– Students and the tutor take more turns in speech, and
use more total words
– Spoken turns are on average shorter
– The ratio of student to tutor language production is
higher in text
Learning Correlations after
Controlling for Pretest
Dependent Measure
Ave. Stud. Words/Turn
Intercept: Stud. Words/Turn
Ave. Tut. Words/Turn
Human
Spoken (14)
R
p
-.209 .49
-.441 .13
-.086 .78
Human
Typed (20)
R
p
.515 .03
.593 .01
.536 .02
Additional Analyses:
Spoken Human Tutoring
Dependent Measure
Tot. Stud. Questions
Ave. Stud. Questions/Dial
Mean Controlled
R
p
35.29 -.500 .08
3.86
-.477
.10
13.55
-.489
.09
Std. Stud-Tut Word Ratio/Dial
0.14 -.584
.04
Std. Stud-Tut Words/Turn/Dial
0.22 -.640
.02
Std. Tut. Questions/Dial
Removing Student “Groundings”:
Spoken Human Tutoring
Dependent Measure
Mean
Controlled
R
p
Tot. Student Words
2133.57 -.298 .32
Tot. Student Turns
251.36
-.281 .35
Ave. Student Words/Turn 8.33
-.243 .42
Std. Student Turns/Dial.
-.478 .10
15.79
Discussion
 Measures
correlating with learning in the typed condition do
not correlate in the spoken condition
– Typed results suggest that students who give longer answers, or
who are inherently verbose, learn more
– Initial analyses removing “groundings” do not change spoken
results
 Deeper
analyses needed (requires manual coding)
– do longer student turns reveal more reasoning and explanation?
– do longer tutor turns mean better explanations or feedback?
– results need to be further examined for student question types,
substantive contributions versus groundings, tutor moves, etc.
Computer Tutoring: Experiment 2
 Same
physics problems, web interface, and experimental
procedure as Experiment 1; however
– only 5 problems (dialogues) per student
– pretest taken after background reading
– strict turn taking enforced in both conditions
 Typed
dialogue condition (23 students, 115 dialogues)
– Why2-Atlas computer tutor
– student and tutor interact via text-based chat interface
 Spoken
–
–
–
–
dialogue condition (20 students, 100 dialogues)
ITSPOKE computer tutor
student and tutor interact through microphone and headset
utterances displayed when student or ITSPOKE finished speaking
speech recognition output rather than actual student utterances
Spoken Computer Tutoring Excerpt
ITSPOKE: What else do you need to know to find the box's
acceleration?
Student:
the direction
ASR: add directions
ITSPOKE : If you see a body accelerate, what caused that
acceleration?
Student:
force
ITSPOKE : Good job. Say there is only one force acting on
the box. How is this force, the box's mass, and its
acceleration related?
Student:
velocity
ITSPOKE : Could you please repeat that? ASR: REJECT
Student:
velocity
Learning and Training Time
Dependent
Measure
Pretest Mean (std dev.)
Computer Computer
Spoken (20) Typed (23)
(ITSPOKE) (Why2Atlas)
.48 (.17)
.49 (.20)
Posttest Mean (std dev.)
.69 (.18)
.70 (.16)
Adj. Posttest Mean (std dev.) .69 (.13)
.69 (.13)
Dialog Time (std dev.)
97.85 (32.8) 68.93 (29.0)
Discussion
 There
was a robust main effect for test phase
(p=0.000), indicating that students in both
conditions learned during tutoring
 The adjusted posttest scores were not reliably
different (p=0.950), suggesting that students
learned the same in both conditions
 Students in the typed condition completed their
tutoring in less time than in the spoken
condition (p=0.004)
New Computer Tutoring Dialogue
Characteristics
 Why2-Atlas
and ITSPOKE conditions
– Total Subdialogues per Knowledge Construction
Dialogue (KCD)
 Only
ITSPOKE (speech recognition) condition
– Word Error Rate
– Concept Accuracy
– Timeouts
– Rejections
Computer Tutoring Dialogue
Characteristics (means)
Dependent Measure
Tot. Stud. Words
Tot. Stud. Turns
Ave. Stud. Words/Turn
Slope: Stud. Words/Turn
Intercept: Stud. Words/Turn
Tot. Tut. Words
Tot. Tut. Turns
Ave. Tut. Words/Turn
Stud-Tut Tot. Words Ratio
Stud-Tut Words/Turn Ratio
Tot. Subdialogues/KCD
Spoken
296.85
116.75
2.42
-.02
3.21
6314.90
148.20
42.11
.05
.06
3.29
Typed
238.17
87.96
2.77
-.00
2.88
4972.61
110.22
44.33
.05
.06
1.98
p
.12
.02
.29
.02
.40
.03
.01
.06
.57
.64
.01
Learning Correlations after
Controlling for Pretest
Dependent Measure
Tot. Stud. Words
Tot. Subdialogues/KCD
Spoken
Typed
(ITSPOKE)
(Why2-Atlas)
R
.394
- .018
p
R
.10 .050
.94 - .457
p
.82
.03
Additional Analyses: Spoken
Computer Tutoring
Dependent Measure
Mean
Tot. Dial. Time (min)
Ave. Dial. Time (min)
Std. Dial. Time (min)
Std. Tot. Stud. Words
Word Error Rate
Concept Accuracy
Tot. Timeouts
Tot. Rejects
97.85
17.07
9.99
42.39
32.45
0.92
5.50
8.15
Controlled
R
p
.580 .01
.580 .01
.541 .02
.457 .05
-.201 .41
.113 .65
.296 .22
-.244 .31
Learning Correlations for 7 ITSPOKE
Students with Pretest < .4
Dependent Measure
Slope: Student
Words/Turn
Intercept: Student
Words/Turn
Mean
Controlled
R
p
-.03
-.877
.02
3.06
.900
.02
Discussion
 Means
across conditions are no longer
significantly different for many measures
– total words produced by students
– average length of student turns and initial verbosity
– ratios of student to tutor language production
 Different
measures again correlate with learning
– Speech: student language production and time
– Text: less subdialogues/KCD
– Degradation due to speech does not correlate
Outline
Introduction and Background
 The ITSPOKE System and Corpora
 A Study of Spoken versus Typed Dialogue Tutoring

– Human tutoring condition
– Computer tutoring condition

Current Directions and Summary
Current and Future Directions
 Data Analysis
– Deeper coding for question types and other dialogue phenomena
 ITSPOKE
–
–
–
–
version 2
Pre-recorded prompts and domain-specific TTS
Shorter tutor prompts and/or changed display procedure
Barge-in, Always Available Vocabulary
Monitoring and adaptation capabilities
 Data
Collection
– Additional human tutors and computer voices
– Other dialogue evaluation metrics
Summary
 Goal:
generate an empirically-based understanding of the
implications of adding speech to text-based dialogue tutors
 Accomplishments
– Completion of ITSPOKE (version1)
– Transcription, “annotation”, and preliminary analysis of two spoken
tutoring corpora (human tutoring, computer tutoring)
– Initial empirical comparisons of typed and spoken tutorial dialogues
(performance evaluation, correlation of dialogue characteristics with
learning)
 Results
will impact the design of future systems incorporating
speech, by highlight the performance gains that can be
expected, and the requirements for their achievement
References

Diane J. Litman, Carolyn P. Rose, Kate Forbes-Riley, Kurt
VanLehn, Dumisizwe Bhembe, and Scott Silliman. Spoken
Versus Typed Human and Computer Dialogue Tutoring. To
appear, Proceedings of the Seventh International Conference on
Intelligent Tutoring Systems (ITS), Maceio, Brazil, AugustSeptember 2004.

Diane J. Litman and Scott Silliman. ITSPOKE: An Intelligent
Tutoring Spoken Dialogue System. In Proceedings of the
Human Language Technology Conference: 4th Meeting of the
North American Chapter of the Association for Computational
Linguistics (HLT/NAACL) (Companion Proceedings), Boston,
MA, May 2004.

Related papers available at
http://www.cs.pitt.edu/~litman/itspoke.html
Acknowledgments
 Kurt VanLehn
 The
and the Why2 Team
ITSPOKE Group
– Kate Forbes-Riley, LRDC, Research Associate
– Scott Silliman, LRDC, Programmer
– Art Ward, Intelligent Systems, PhD Student
– Alison Huettner, LRDC, Research Associate
Thank You!
Questions?
Zero-Order Learning Correlations
Dependent Measure
Tot. Stud. Words
Ave. Stud. Words/Turn
Slope: Stud. Words/Turn
Intercept: Stud. Words/Turn
Tot. Tut. Words
Ave. Tut. Words/Turn
Human
Spoken (14)
R
p
-.473 .09
-.167 .57
-.275 .34
-.176 .55
-.482 .08
-.139 .64
Human
Typed (20)
R
p
.065 .78
.491 .03
-.375 .10
.625 .00
.027 .91
.496 .03
Human-Human Corpus Transcription and Annotation
Human-Computer Excerpt
Tutor26:
Let me ask my question in a more general way. What happens to the
velocity of a body when there is no force acting on it?
Student27: dammit (ASR: it is)
Tutor28 : Could you please repeat that?
Student29 : same (ASR: i same)
Tutor30 : Right. And what happens to the HORIZONTAL velocity of a body when
there is no HORIZONTAL force acting on it?
Student31: zero (ASR: the zero)
Tutor32 : Well... OK, let's consider how forces in the vertical direction affect the
motion of a body in a horizontal direction in a different scenario <…omitted…>
Student33: oh gravity you already said this (ASR: beats gravity you're exert less)
Tutor34:
Fine. Are there any other forces acting on the apple as it falls?
Student35: no why are you doing this again (ASR: no y and to it yes)
Tutor36:
Correct. The only force acting on the apple as it falls to the earth is the
earth's gravitational force. In which direction does gravitational force act?
Student37: downward you computer (ASR: downward you computer)
Why2 Conceptual Physics
Tutoring