Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer...

60
Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development Center University of Pittsburgh HLT-NAACL 2006

Transcript of Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer...

Page 1: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Spoken Dialogue for Intelligent Tutoring Systems:

Opportunities and Challenges

Diane Litman

Computer Science Department

Learning Research & Development Center

University of Pittsburgh

HLT-NAACL 2006

Page 2: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Outline

Motivation and History The ITSPOKE System and Corpora Opportunities and Challenges

– Performance Evaluation– Affective Reasoning– Discourse Analysis

Summing Up

Page 3: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

What is Tutoring?

• “A one-on-one dialogue between a teacher and a student for the purpose of helping the student

learn something.”

[Evens and Michael 2006]

• Human Tutoring Excerpt [Thanks to Natalie Person and Lindsay Sears,

Rhodes College]

Page 4: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Intelligent Tutoring Systems

Students who receive one-on-one instruction perform as well as the top two percent of students who receive traditional classroom instruction [Bloom 1984]

Unfortunately, providing every student with a personal human tutor is infeasible– Develop computer tutors instead

Page 5: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Tutorial Dialogue Systems Why is one-on-one tutoring so effective?

“...there is something about discourse and natural language (as opposed to sophisticated pedagogical strategies) that explains the effectiveness of unaccomplished human [tutors].”

[Graesser, Person et al. 2001]

Working hypothesis regarding learning gains– Human Dialogue > Computer Dialogue > Text

Page 6: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Spoken Tutorial Dialogue Systems Most human tutoring involves face-to-face

spoken interaction, while most computer dialogue tutors are text-based

Can the effectiveness of dialogue tutorial systems be further increased by using spoken interactions?

Page 7: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

A Brief History 1970 – Mid 1980s

– SCHOLAR (Carbonell) – WHY (Stevens and Collins) – SOPHIE (Burton and Brown)– Meno-Tutor (Woolf and McDonald) …

Late 1980s - 1990s– CIRCSIM-Tutor (Evens, Michael and Rovick)– SHERLOCK II (Lesgold) – Unix Consultant (Wilensky et al. )– EDGE (Cawsey) …

Currently…– Why2-AutoTutor (Graesser et al.) (speech synthesis)– Why2-Atlas (VanLehn et al.)– CyclePad (Rose et al.)– Beetle (Moore et al.)– DIAG-NLG (Di Eugenio)– SCoT (Peters et al.) (spoken dialogue)– ITSPOKE (Litman et al.) … (spoken dialogue)

Page 8: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Potential Benefits of Speech: I

Self-explanation correlates with learning [Chi et al. 1994] and occurs more in speech [Hausmann and Chi 2002]– Tutor: The right side pumps blood to the lungs, and the left side

pumps blood to the other parts of the body. Could you explain how that works?

– Student 1 (self-explains): So the septum is a divider so that the blood doesn't get mixed up. So the right side is to the lungs, and the left side is to the body. So the septum is like a wall that divides the heart into two parts...it kind of like separates it so that the blood doesn't get mixed up...

– Student 2 (doesn’t self-explain): right side pumps blood to lungs

Page 9: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Potential Benefits of Speech: I

Self-explanation correlates with learning [Chi et al. 1994] and occurs more in speech [Hausmann and Chi 2002]– Tutor: The right side pumps blood to the lungs, and the left side

pumps blood to the other parts of the body. Could you explain how that works?

– Student 1 (self-explains): So the septum is a divider so that the blood doesn't get mixed up. So the right side is to the lungs, and the left side is to the body. So the septum is like a wall that divides the heart into two parts...it kind of like separates it so that the blood doesn't get mixed up...

– Student 2 (doesn’t self-explain): right side pumps blood to lungs

Page 10: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Potential Benefits of Speech: I

Self-explanation correlates with learning [Chi et al. 1994] and occurs more in speech [Hausmann and Chi 2002]– Tutor: The right side pumps blood to the lungs, and the left side

pumps blood to the other parts of the body. Could you explain how that works?

– Student 1 (self-explains): So the septum is a divider so that the blood doesn't get mixed up. So the right side is to the lungs, and the left side is to the body. So the septum is like a wall that divides the heart into two parts...it kind of like separates it so that the blood doesn't get mixed up...

– Student 2 (doesn’t self-explain): right side pumps blood to lungs

Page 11: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Potential Benefits of Speech: II

Speech contains prosodic information, providing new sources of information about the student for dialogue adaptation [Fox 1993; Litman and Forbes-Riley 2003; Pon-Barry et al. 2005]

A correct but uncertain student turn– ITSPOKE: How does his velocity compare to that of

his keys?– STUDENT: his velocity is constant

Page 12: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Potential Benefits of Speech: III Spoken computational environments may foster

social relationships that may enhance learning– AutoTutor [Graesser et al. 2003]

Page 13: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Potential Benefits of Speech: IV

• Some applications inherently involve spoken language– Spoken Conversational Interface for

Language Learning

[Thanks to Stephenie Seneff, MIT and Cambridge]

– Reading Tutors [Mostow, Cole]

• Others require hands-free interaction– Circuit Fix-It Shop [Smith 1992]

Page 14: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Why Should NLP Researchers Care?

Many reasons why tutoring researchers are interested in spoken dialogue

Why should spoken dialogue researchers become interested in tutoring?– Tutoring applications differ in many ways from

typical spoken dialogue applications– Opportunities and Challenges!

Page 15: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Outline

Motivation and History The ITSPOKE System and Corpora Opportunities and Challenges

– Performance Evaluation– Affective Reasoning– Discourse Analysis

Summing Up

Page 16: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

• Back-end is Why2-Atlas system [VanLehn et al. 2002]• Sphinx2 speech recognition and Cepstral text-to-speech

Page 17: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

• Back-end is Why2-Atlas system [VanLehn et al. 2002]• Sphinx2 speech recognition and Cepstral text-to-speech

Page 18: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

• Back-end is Why2-Atlas system [VanLehn et al. 2002]• Sphinx2 speech recognition and Cepstral text-to-speech

Page 19: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Two Types of Tutoring Corpora Human Tutoring

– 14 students / 128 dialogues (physics problems)– 5948 student turns, 5505 tutor turns

Computer Tutoring– ITSPOKE v1

» 20 students / 100 dialogues » 2445 student turns, 2967 tutor turns

– ITSPOKE v2» 57 students / 285 dialogues» both synthesized and pre-recorded tutor voices

Page 20: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

ITSPOKE Experimental Procedure

College students without physics– Read a small background document– Took a multiple-choice Pretest – Worked 5 problems (dialogues) with ITSPOKE – Took an isomorphic Posttest

Goal was to optimize Learning Gain– e.g., Posttest – Pretest

Page 21: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Outline

Motivation and History The ITSPOKE System and Corpora Opportunities and Challenges

– Performance Evaluation– Affective Reasoning– Discourse Analysis

Summing Up

Page 22: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Predictive Performance Modeling

Opportunity – Spoken dialogue system evaluation methodologies

can improve our understanding of how dialogue facilitates student learning [Forbes-Riley and Litman 2006]

Challenges– How to measure system performance?

– What are predictive interaction parameters?

Page 23: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Predictive Performance Modeling Understand why a spoken dialogue system fails or succeeds PARADISE [Walker et al. 1997]

– Measure parameters (interaction costs and benefits) and performance in a system corpus

– Train model via multiple linear regression over parameters, predicting performance

System Performance = ∑ wi * pi

– Test model on new corpus

– Predict performance during future system design

n

i=1

Page 24: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Challenges

System Performance – Prior evaluations used User Satisfaction– Is Student Learning more relevant for the tutoring

domain?

Interaction Parameters– Prior applications used Generic parameters – Are Task-Specific and Affective parameters also

useful?

Page 25: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Findings Using PARADISE to predict Learning

– Posttest = .86 * Time + .65 * Pretest - .54 * #Neutrals Useful Predictors

– Traditional parameters» e.g., Elapsed Time, Dialogue and Turn Length

– New parameters» e.g., Affect, Correctness

Page 26: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Contrasts with Non-Tutorial Dialogue

User Satisfaction models are less useful– Tutoring systems are not designed to maximize User

Satisfaction Interaction parameters for learning

– Posttest = .86 * Time + .65 * Pretest - .54 * #Neutrals» longer dialogues are better» speech recognition problems don’t seem to matter» lack of some types of affect is bad

Page 27: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Contrasts with Non-Tutorial Dialogue

User Satisfaction models are less useful– Tutoring systems are not designed to maximize User

Satisfaction Interaction parameters for learning

– Posttest = .86 * Time + .65 * Pretest - .54 * #Neutrals» longer dialogues are better» speech recognition problems don’t seem to matter» lack of some types of affect is bad

Page 28: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Contrasts with Non-Tutorial Dialogue

User Satisfaction models are less useful– Tutoring systems are not designed to maximize User

Satisfaction Interaction parameters for learning

– Posttest = .86 * Time + .65 * Pretest - .54 * #Neutrals» longer dialogues are better» speech recognition problems don’t seem to matter» lack of some types of affect is bad

Page 29: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Outline

Motivation and History The ITSPOKE System and Corpora Opportunities and Challenges

– Performance Evaluation– Affective Reasoning– Discourse Analysis

Summing Up

Page 30: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Detecting and Responding to Student Affective States

Opportunity – Affective spoken dialogue system technology can

improve student learning and other measures of performance [Aist et al. 2002; Pon-Barry et al. 2006]

Challenges– What to detect?

– How to respond?– Pedagogical versus spoken dialogue performance?

Page 31: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Monitoring Student State (motivation)

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)

Page 32: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Affective Spoken Dialogue Systems: Standard Methodology

Manual Annotation of Affect and Attitudes– Naturally-occurring spoken dialogue data [Ang et al.

2002; Lee et al. 2002; Batliner et al. 2003; Devillers et al. 2003; Shafran et al. 2003; Liscombe et al. 2005]

Prediction via Machine Learning– Automatically extract features from user turns– Use different feature sets (e.g. prosodic, lexical) to

predict affect– Significant reduction of baseline error

Page 33: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Challenge 1: What “emotions” to detect?

Communicator and Customer Care Systems – Negative: Angry, Annoyed, Frustrated, Tired

– Positive/Neutral: Amused, Cheerful, Delighted, Happy, Serious

[Ang et al. 2002; Shafran et al. 2003; Lee and Narayanan 2005; Liscombe et al. 2005]

Page 34: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Challenge 1: What “emotions” to detect?

Communicator and Customer Care Systems – Negative: Angry, Annoyed, Frustrated, Tired

– Positive/Neutral: Amused, Cheerful, Delighted, Happy, Serious

[Ang et al. 2002; Shafran et al. 2003; Lee and Narayanan 2005; Liscombe et al. 2005]

Tutorial Dialogue Systems – Negative: Angry, Annoyed, Frustrated, Bored, Confused,

Uncertain, Contempt, Disgusted, Sad

– Positive/Neutral: Certain, Curious, Enthusiastic, Eureka

[Litman and Forbes-Riley 2006, D’Mello et al. 2006]

Page 35: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Example Student States in ITSPOKE

ITSPOKE: What else do you need to know to find the box‘s acceleration?

Student: the direction [UNCERTAIN] ITSPOKE : If you see a body accelerate, what caused that

acceleration?Student: force [CERTAIN] 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 [UNCERTAIN] ITSPOKE : Could you please repeat that?Student: velocity [ANNOYED]

Page 36: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Challenge 2: How to respond?• In tutoring, not all negatively-valenced emotions are bad!

– While frustration/anger/annoyance is often frustrating…

– Frustration can also be an opportunity to learn

• Example from AutoTutor– neutral flow confusion frustration neutral

[Thanks to Sidney D‘Mello and Arthur Graesser,

University of Memphis]

Page 37: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Example from ITSPOKE

ITSPOKE: What is the net force acting on the truck equal to?

Student: I don’t know [Uncertain, Frustrated]

ITSPOKE: Since net force is defined as the vector sum of all the forces exerted on an object, let's first

find the forces acting on the truck. Try to name them.

Student: The impact force, the normal force, and gravity[Certain, Neutral]

ITSPOKE: Yep.

Page 38: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Uncertainty is also a Learning Opportunity Uncertainty represents one type of learning impasse

[VanLehn et al. 2003]:

An impasse motivates a student to take an active role in constructing a better understanding of the principle.

Uncertainty is also associated with cognitive disequilibrium [Craig et al. 2004]:

A state of failed expectations causing deliberation aimed at restoring equilibrium

– Uncertainty positively correlates with learning

Page 39: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Do Human Tutors Respond to Student Uncertainty?

A data-driven method for designing dialogue systems adaptive to student state [Forbes-Riley and Litman 2005]– extraction of “dialogue bigrams” from annotated

human tutoring corpora

– χ2 analysis to identify dependent bigrams

– generalizable to any domain with corpora labeled for user state and system response

Page 40: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Example Human Tutoring Excerpt

S: So the- when you throw it up the acceleration will stay the same? [Uncertain]

T: Acceleration uh will always be the same because there is- that is being caused by force of gravity which is not

changing. [Restatement, Expansion]

S: mm-k. [Neutral]

T: Acceleration is– it is in- what is the direction uh of this acceleration- acceleration due to gravity?

[Short Answer Question]

S: It’s- the direction- it’s downward. [Certain]

T: Yes, it’s vertically down. [Positive Feedback, Restatement]

Page 41: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Bigram Dependency Analysis

EXPECTEDTutor

IncludePosTutor

OmitsPos

neutral 439.46 2329.54

certain 175.21 928.79

uncertain 129.51 686.49

mixed 36.82 195.18

OBSERVEDTutor

IncludesPos

Tutor OmitsPos

neutral 252 2517

certain 273 832

uncertain 185 631

mixed 71 161

χ2 = 225.92 (critical χ2 value at p = .001 is 16.27)- “Student Certainness – Tutor Positive Feedback” Bigrams

Page 42: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Bigram Dependency Analysis (cont.)

EXPECTEDIncludes

Pos

Omits

Pos

neutral 439.46 2329.54

OBSERVEDIncludes

Pos

Omits

Pos

neutral 252 2517

- Less Tutor Positive Feedback after Student Neutral turns

Page 43: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Bigram Dependency Analysis (cont.)

EXPECTEDIncludes

Pos

Omits

Pos

neutral 439.46 2329.54

certain 175.21 928.79

uncertain 129.51 686.49

mixed 36.82 195.18

OBSERVEDIncludes

Pos

Omits

Pos

neutral 252 2517

certain 273 832

uncertain 185 631

mixed 71 161

- Less Tutor Positive Feedback after Student Neutral turns- More Tutor Positive Feedback after “Emotional” turns

Page 44: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Findings Statistically significant dependencies exist

between students’ state of certainty and the responses of an expert human tutor– After uncertain, tutor Bottoms Out and avoids

expansions – After certain, tutor Restates– After mixed, tutor Hints– After any emotion, tutor increases Feedback

Dependencies suggest adaptive strategies for implementation in computer tutoring systems

Page 45: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Challenge 3: Pedagogical versus spoken dialogue performance?

Negative user emotions (e.g. frustration) are often associated with speech recognition problems [Boozer et al. 2003; Goldberg et al. 2003]– Is this also true in tutoring?

Speech recognition problems negatively correlate with user satisfaction [Walker et al. 2002, Pon-Barry et al. 2006] – Is this also true for learning?

Page 46: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Findings Statistically significant dependencies exist between student

state and speech recognition problems [Rotaru and Litman 2006]– Frustrated/Angry turns are rejected more than expected

– Uncertain turns have more problems than expected (certain turns have less)

– Incorrect turns have more problems than expected (correct turns have less)

Learning opportunities (e.g. uncertain and incorrect student states) have more speech recognition problems– However, speech recognition problems have not negatively

correlated with learning [Litman and Forbes-Riley 2005, Pon-Barry et al. 2005]

Page 47: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Outline

Motivation and History The ITSPOKE System and Corpora Opportunities and Challenges

– Performance Evaluation– Affective Reasoning– Discourse Analysis

Summing Up

Page 48: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Discourse Structure

Opportunity – Dialogues with tutoring systems have more complex

hierarchical discourse structures compared to many other types of dialogues

Challenges– How can discourse structure be exploited in the

context of spoken dialogue systems?

Page 49: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Exploiting Discourse Structure (Motivation)

Average ITSPOKE dialogue is 20 minutes Student turns are hierarchically structured

– Level 1 : 1350 (57.3%)– Level 2 : 643 (27.3%)– Level 3 : 248 (10.5%)– Levels 4-6 :113 (4.8%)

Page 50: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Discourse structureAnnotation and Transitions Based on the Grosz & Sidner theory of discourse structure

– Discourse segment Discourse segment purpose

– Hierarchy of discourse segments

Tutoring information encoded in a hierarchical structure– Human tutor manually authored dialogue paths for ITSPOKE

– Automatic traversal of logs places utterances into the structure

Q1 Q2 Q3

Q2.1 Q2.2

Page 51: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Q1 Q2 Q3

Q2.1 Q2.2

ITSPOKE behavior &Discourse structure annotation

Page 52: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Q1 Q2 Q3

Q2.1 Q2.2

Discourse structure transitions

Page 53: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Findings

Student correctness is predictive of student learning, but only after particular discourse transitions [Rotaru and Litman 2006]– e.g., After Pops (PopUp, PopUpAdvance)

» incorrect turns negatively predict learning» correct turns positively predict learning

Student certainness is more predictive only after particular transitions

Page 54: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Findings (cont.)

While single discourse transitions are not predictive of learning, patterns in the discourse structure are– e.g., Advance-Advance and Push-Push both positively

correlate with learning

Statistically significant dependencies exist between discourse transitions and speech recognition– e.g., after both Pushes and Pops, more misrecognitions

Page 55: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Outline

Motivation and History The ITSPOKE System and Corpora Opportunities and Challenges

– Performance Evaluation– Affective Reasoning– Discourse Analysis

Summing Up

Page 56: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Summing Up: I

Spoken Dialogue Systems are of great interest to researchers in Intelligent Tutoring– One-on-one tutoring is a powerful technique for helping

students learn– Natural language dialogue contributes in a powerful way

to the efficacy of one-on-one-tutoring– Using presently available NLP technology, computer

tutors can be built and can serve as a valuable aid to student learning

Page 57: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Summing Up: II

Intelligent Tutoring in turn provides many opportunities and challenges for researchers in Spoken Dialogue Systems – Performance Evaluation– Affective Reasoning– Discourse Analysis

Page 58: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Summing Up: II

Intelligent Tutoring in turn provides many opportunities and challenges for researchers in Spoken Dialogue Systems – Performance Evaluation– Affective Reasoning– Discourse Analysis– and many more!

» Initiative, Cohesion/Coherence, Dialogue Acts, Turn-Taking, Reinforcement Learning, User Simulation, Question-Answering

Page 59: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Acknowledgements ITSPOKE group

– Hua Ai, Kate Forbes-Riley, Alison Huettner, Beatriz Maeireizo-Tokeshi, Greg Nicholas, Amruta Purandare, Mihai Rotaru, Scott Silliman, Joel Tetrault, Art Ward

– Columbia Collaborators: Julia Hirschberg, Jackson Liscombe, Jennifer Venditti

NLP@Pitt– Jan Wiebe, Rebecca Hwa, Wendy Chapman, Paul Hoffmann, Behrang

Mohit, Carol Nichols, Swapna Somasundaran, Theresa Wilson, Chenhai Xi Why2-Atlas and Human Tutoring groups

– Kurt Vanlehn, Pam Jordan, Uma Pappuswamy, Carolyn Rose– Micki Chi, Scotty Craig, Bob Hausmann, Margueritte Roy

Art Graesser, Natalie Person, Sidney D’Mello, Lindsay Sears Stephenie Seneff Martha Evens

Page 60: Spoken Dialogue for Intelligent Tutoring Systems: Opportunities and Challenges Diane Litman Computer Science Department Learning Research & Development.

Thank You!

Questions?

Further Information– http://www.cs.pitt.edu/~litman/itspoke.html

And in September, come to Pittsburgh for Interspeech 2006!