XTutor: an Intelligent Tutor System for Science and Math Based on Excel (2009)
Roxana Gheorghiu, Kurt Vanlehn
Abstract. VanLehn argued that an essential feature of many intelligent tutoring systems (ITSs) is that they provide feedback and hints on every step of a multi-step solution.But if step-based...
Productive Dialog During Collaborative Problem Solving (2009)
Abstract: Collaboration is an important problem-solving skill; however, novice collaboration generally benefits from some kind of support. One possibility for supporting productive conversations...
Abstract. One important goal of Intelligent Tutoring Systems (ITSs) is to bring students up to the same level of mastery. We showed that an ITS teaching a domain-independent problem-solving strategy...
Abstract. Authoring the knowledge base for an intelligent tutoring system (ITS) is difficult and time consuming. In many ITS, the knowledge base is used for solving problems, so authoring it is an...
Traditional methods of evaluating student programs are not always appropriate for assessment of different instructional interventions. They tend to focus on the final product rather than on the...
Porting an Intelligent Tutoring System across Domains (2009)
Abstract. One possible approach to reducing the cost of developing an intelligent tutoring system (ITS) is to reuse the components of an existing ITS. We used this approach to develop an Andes...
Michael A. Ringenberg, Kurt Vanlehn
Abstract. Students who complete an introductory physics course often do not have a good conceptual understanding of the principles taught. There have been various attempts at increasing conceptual...
Trialog: How Peer Collaboration Helps Remediate Errors in an ITS (2009)
Many intelligent tutoring systems (ITSs) offer feedback and guidance through structured dialogs with their students, which often take the form of a sequence of hints. However, it is often difficult...
Bridging Principles and Examples through Analogy and Explanation (2009)
Timothy J. Nokes, Kurt Vanlehn
Abstract: Previous research in cognitive science has shown that analogical comparison and selfexplanation are two powerful learning activities that can improve conceptual learning in laboratory...
Although cognitive science has discovered several methods for increasing the learning of complex skills, such as physics problem solving, detailed examination of verbal protocols suggests there is...
Art Graesser, Arthur C. Graesser, Danielle S. Mcnamara, Kurt Vanlehn
It is well documented that most students do not have adequate proficiencies in inquiry and metacognition, particularly at deeper levels of comprehension that require explanatory reasoning. The...
Scaffolding Problem Solving with Annotated Worked-Out Examples to Promote Deep Learning (2008)
Michael A. Ringenberg, Kurt Vanlehn
Abstract. This study seeks to compare the relative utility for learning college-level physics of intelligent tutoring systems that have procedural based hints and worked-out examples. In order to...
Accuracy of Tutors ’ Assessments of their Students by Tutoring Context (2008)
Stephanie A. Siler, Kurt Vanlehn
In this study we compared the accuracy of tutors’ assessments of their students ’ general competence, conceptual knowledge and affective state in two different tutoring contexts: face-to-face...
This chapter describes how intelligent tutoring systems can be used for assessment. It begins by describing intelligent tutoring systems and distinguishing them from an older, more widely available...
Bayesian student modeling, user interfaces and feedback: A sensitivity analysis (2008)
The Andes physics tutoring system has a student modeler that uses Bayesian networks. Although the student modeler was evaluated once with positive results, in order to better understand it and...
What’s in a step? Toward general, abstract representations of tutoring system log data (2008)
Kurt Vanlehn, Ken Koedinger, Alida Skogsholm, Adaeze Nwaigwe, Robert G. M, Anders Weinstein, ...
Abstract. The Pittsburgh Science of Learning Center (PSLC) is developing a data storage and analysis facility, called DataShop. It currently handles log data from 6 full-year tutoring systems and...
Self-explaining in the Classroom: Learning Curve Evidence (2008)
Research conducted in the laboratory and classroom has repeatedly found that self-explaining is a useful, self-directed learning strategy. Although the self-explanation effect has been replicated...
Learning from Collaboratively Observing Videos during Problem Solving with Andes (2008)
Scotty D. Craig, Kurt Vanlehn, Soniya Gadgil, Micki Chi
Abstract. Learning by observation has long been a traditional method of learning. Recent work has pointed toward collaboratively observing tutoring as a promising new method for observational...
Domain-Specific and Domain-Independent Interactive Behaviors in Andes (2008)
Abstract. In this study, students studied two different domains in the same
Maxim Makatchev, Kurt Vanlehn, Pamela W. Jordan
Students ’ natural language (NL) explanations in the domain of qualitative mechanics lie in-between unrestricted NL and the constrained NL of “proper ” domain statements. Analyzing such input...
Abstract Resolving Discourse Deictic Anaphors in Tutorial Dialogues (2008)
Pamela W. Jordan, Kurt Vanlehn
Most of the anaphoric resolution algorithms developed so far focus on anaphors with NP antecedents, be it inter-sentential or intrasentential. The main focus of this paper is to resolve various other...
R. Charles Murray, Kurt Vanlehn, Jack Mostow
We propose a decision-theoretic architecture for selecting tutorial discourse actions. DT Tutor, an action selection engine which embodies our approach, uses a dynamic decision network to consider...
Abductive Proofs as Models of Qualitative Reasoning (2008)
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
In this paper we describe an application of weighted abductive theorem proving that is used to create a model of students ’ qualitative reasoning for the Why2-Atlas tutoring system. The system...
A Supervised Clustering Method for Text Classification (2008)
Dumisizwe Bhembe, Pamela W. Jordan, Kurt Vanlehn
Abstract. This paper describes a supervised three-tier clustering method for classifying students ’ essays of qualitative physics in the Why2-Atlas tutoring system. Our main purpose of categorizing...
A Test of the Interaction Hypothesis: Joint-explaining vs. Self-explaining (2008)
It is widely assumed that students learn more from interactive learning situations than non-interactive; however, recent evidence from human tutoring suggests this generalization may not always hold...
Productive Dialog During Collaborative Problem Solving (2008)
Hausmann, Robert G. M., Van De Sande, Brett, Van De Sande, Carla, VanLehn, Kurt
Collaboration is an important problem-solving skill; however, novice collaboration generally benefits from some kind of support. One possibility for supporting productive conversations between...
Hausmann, Robert G. M., Van De Sande, Brett, VanLehn, Kurt
Although cognitive science has discovered several methods for increasing the learning of complex skills, such as physics problem solving, detailed examination of verbal protocols suggests there is...
Is Human Tutoring Always More Effective than Reading (2008)
Abstract. Some previous studies of student learning have demonstrated a strong advantage in favor of human tutoring over a classroom control condition (Bloom, 1984; Cohen et al., 1982). These results...
GRAMY: A Geometry Theorem Prover Capable of Construction (2008)
Abstract. This study investigates a procedure for proving arithmetic-free Euclidean geometry theorems that involve construction. “Construction ” means drawing additional geometric elements in the...
1 Using Bayesian Networks to Manage Uncertainty in Student Modeling (2008)
Cristina Conati, Abigail Gertner, Kurt Vanlehn
Abstract When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it...
Arthur Graesser, Kurt Vanlehn, Carolyn Rosé, Pamela Jordan, Art Graesser
Many of the Intelligent Tutoring Systems that have been developed during the last 20 years have proven to be quite successful, particularly in the domains of mathematics, science, and technology....
Abstract Coached Program Planning: Dialogue-Based Support for Novice Program Design (2008)
Coached program planning is a dialogue-based style of tutoring aimed at helping novices during the early stages of program writing. The intent is to help novices understand and solve problems in...
Porting an Intelligent Tutoring System across Domains (2008)
Abstract. One possible approach to reducing the cost of developing an intelligent tutoring system (ITS) is to reuse the components of an existing ITS. We used this approach to develop an Andes...
Self-explaining in the Classroom: Learning Curve Evidence (2008)
Research conducted in the laboratory and classroom has repeatedly found that self-explaining is a useful, self-directed learning strategy. Although the self-explanation effect has been replicated...
Kurt Vanlehn, Collin Lynch, Kay Schulze, Joel A. Shapiro, Robert Shelby, Linwood Taylor, ...
The Andes system demonstrates that student learning can be significantly increased by upgrading only their homework problem-solving support. Although Andes is called an intelligent tutoring system,...
Learning from Collaboratively Observing Videos during Problem Solving with Andes (2008)
Scotty D. Craig, Kurt Vanlehn, Soniya Gadgil, Micki Chi
Abstract. Learning by observation has long been a traditional method of learning. Recent work has pointed toward collaboratively observing tutoring as a promising new method for observational...
Scaffolding Problem Solving with Annotated Worked-Out Examples to Promote Deep Learning (2008)
Michael A. Ringenberg, Kurt Vanlehn
Abstract. This study compares the relative utility of an intelligent tutoring system that uses procedure-based hints to a version that uses worked-out examples for learning college level physics. In...
D.: Developing pedagogically effective tutorial dialogue tactics: Experiments and a testbed (2008)
Kurt Vanlehn, Pamela Jordan, Diane Litman
Although effective tutorial dialogue strategies are well understood, tutorial tactics that govern brief episodes of tutoring, such as a single step, are not. Because better tactics seem to be crucial...
Abductive Proofs as Models of Qualitative Reasoning (2008)
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
In this paper we describe an application of weighted abductive theorem proving that is used to create a model of students ’ qualitative reasoning for the Why2-Atlas tutoring system. The system...
A Test of the Interaction Hypothesis: Joint-explaining vs. Self-explaining (2008)
It is widely assumed that students learn more from interactive learning situations than non-interactive; however, recent evidence from human tutoring suggests this generalization may not always hold...
1 Using Bayesian Networks to Manage Uncertainty in Student Modeling (2008)
Cristina Conati, Abigail Gertner, Kurt Vanlehn
Abstract When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it...
Abductive Proofs as Models of Qualitative Reasoning (2008)
Maxim Makatchev Maxim, Pamela W. Jordan, Kurt Vanlehn
In this paper we describe an application of weighted abductive theorem proving that is used to create a model of students' qualitative reasoning for the Why2-Atlas tutoring system. The system...
Running head: ANALYSIS OF SYMBOLIC PARAMETER MODELS Analysis of Symbolic Parameter Models (2007)
Thad A. Polk, Kurt Vanlehn, Dirk Kalp
Model-fitting, the problem of finding parameter settings that cause a model to fit given data as closely as possible, is a hard but important problem in cognitive science in general, and in cognitive...
A Hybrid Approach to Content Analysis for Automatic Essay Grading (2007)
Carolyn P. Rosé, Antonio Roque, Dumisizwe Bhembe, Kurt Vanlehn
We present CarmelTC, a novel hybrid text classification approach for automatic essay grading. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two “bag of words ”...
Textbook-Based Physics Training (2007)
Several earlier investigations found that teaching standard textbook physics causes only moderate change in qualitative understanding. Many investigations have tried to explain why teaching textbook...
Abstract Coached Program Planning: Dialogue-Based Support for Novice Program Design (2007)
Coached program planning is a dialogue-based style of tutoring aimed at helping novices during the early stages of program writing. The intent is to help novices understand and solve problems in...
We present a computational framework designed to improve learning from examples by supporting self-explanation – the process of clarifying and making more complete to oneself the solution of an...
1 Teaching meta-cognitive skills: implementation (2007)
and evaluation of a tutoring system to guide selfexplanation while learning from examples.
Arthur Graesser, Kurt Vanlehn, Carolyn Ros, Pamela Jordan, Art Graesser
Many of the Intelligent Tutoring Systems that have been developed during the last 20 years have proven to be quite successful, particularly in the domains of mathematics, science, and technology....
Cristina Conati, Abigail S. Gertner, Kurt Vanlehn
Abstract. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES ' student model uses a Bayesian network to do long-term...
1 Teaching meta-cognitive skills: implementation (2007)
and evaluation of a tutoring system to guide selfexplanation while learning from examples.
Bayesian Student Modeling, User Interfaces and Feedback: A Sensitivity Analysis (2007)
The Andes physics tutoring system has a student modeler that uses Bayesian networks. Although the student modeler was evaluated once with positive results, in order to better understand it and...
Abstract. Explicit instruction in a problem-solving strategy accelerated learning not
Adaeze Nwaigwe, Kenneth Koedinger, Kurt Vanlehn, Anders Weinstein
Abstract. It is becoming a standard technique to use learning curves as part of evaluation of intelligent tutoring systems [1,2,3], but such learning curves require a method for attributing errors....
Abstract. Explicit instruction in a problem-solving strategy accelerated learning not
ASPM2: Progress Toward the Analysis of Symbolic Parameter Models (2006)
Polk, Thad A., VanLehn, Kurt, Kalp, Dirk
Model-fitting, the problem of finding parameter settings that cause a model to fit given data as closely as possible, is a hard but important problem in cognitive science in general, and in cognitive...
A comparison of decision-theoretic, fixed-policy and random tutorial action selection (2006)
R. Charles Murray, Kurt Vanlehn
Abstract. DT Tutor (DT), an ITS that uses decision theory to select tutorial actions, was compared with both a Fixed-Policy Tutor (FT) and a Random Tutor (RT). The tutors were identical except for...
Maxim Makatchev, Kurt Vanlehn, Pamela W. Jordan, Umarani Pappuswamy
Students' natural language (NL) explanations in the domain of qualitative mechanics lie in-between unrestricted NL and the constrained NL of "proper" domain statements. Analyzing such...
Teaching the tacit knowledge of programming to novices with natural language tutoring (2005)
H. Chad Lane, Kurt Vanlehn, H. Chad Lane
For beginning programmers, inadequate problem solving and planning skills are among the most salient of their weaknesses. In this paper, we test the efficacy of natural language tutoring to teach and...
Effects of dissuading unnecessary help requests while providing proactive help (2005)
R. Charles Murray, Kurt Vanlehn
Abstract. We tested effects of dissuading students from requesting help unless they
Mixed Language Processing in the Why2-Atlas Tutoring System (2005)
Maxim Makatchev, Brian S. Hall, Pamela W. Jordan, Umarani Pappuswamy, Kurt Vanlehn
When dealing with a natural language interaction about a formal domain, a number of phenomena occur. They include interspersing natural language with formulas, various degrees of formality, and...
Logic-Based Natural Language Understanding in Intelligent Tutoring Systems (2005)
Octav Popescu, Jaime Carbonell, Lori Levin, Kurt Vanlehn
High-precision Natural Language Understanding is needed in Geometry Tutoring to accurately determine the semantic content of students' explanations. The thesis presents a Natural Language...
Advanced Geometry Tutor: an Intelligent Tutor that Teaches Proof-Writing with Construction (2005)
Abstract: Two problem solving strategies, forward chaining and backward chaining, were compared to see how they affect students ' learning of geometry theorem proving with construction. In order...
Effects of dissuading unnecessary help requests while providing proactive help (2005)
R. Charles Murray, Kurt Vanlehn
Abstract. We tested effects of dissuading students from requesting help unless they
Taking control of redundancy in scripted tutorial dialogue (2005)
Pamela W. Jordan, Patricia Albacete, Kurt Vanlehn
Abstract. We describe extensions to a finite-state dialogue manager and its author scripting language that enable control over content repetition during tutorial dialogue.
The Andes physics tutoring system: five years of evaluations (2005)
Kurt Vanlehn, Collin Lynch, Kay Schulze, Joel A. Shapiro, Robert Shelby, Linwood Taylor, ...
Abstract. Andes is a mature intelligent tutoring system that has helped hundreds of students improve their learning of university physics. It replaces pencil and paper problem solving homework....
A multi-tier NL-knowledge clustering for classifying students’ essays (2005)
Dumisizwe Bhembe, Pamela W. Jordan, Kurt Vanlehn
In this paper, we describe a multi-tier Natural Language (NL) clustering approach to text classification for classifying students ’ essays for tutoring applications. The main task of the classifier...
Teaching the tacit knowledge of programming to novices with natural language tutoring (2005)
Kurt Vanlehn, H. Chad Lane, H. Chad Lane
For beginning programmers, inadequate problem solving and planning skills are among the most salient of their weaknesses. In this paper, we test the efficacy of natural language tutoring to teach and...
Looking Ahead to Select Tutorial Actions: A Decision-Theoretic Approach (2004)
Murray, R. Charles, Vanlehn, Kurt, Mostow, Jack
We propose and evaluate a decision-theoretic approach for selecting tutorial actions by looking ahead to anticipate their effects on the student and other aspects of the tutorial state. The approach...
Looking Ahead to Select Tutorial Actions: A Decision-Theoretic Approach (2004)
Murray, R. Charles, Vanlehn, Kurt, Mostow, Jack
We propose and evaluate a decision-theoretic approach for selecting tutorial actions by looking ahead to anticipate their effects on the student and other aspects of the tutorial state. The approach...
Modeling students’ reasoning about qualitative physics: Heuristics for abductive proof search (2004)
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
Abstract. We describe a theorem prover that is used in the Why2-Atlas tutoring system for the purposes of evaluating the correctness of a student’s essay and for guiding feedback to the student....
Pamela W. Jordan, Pamela W. Jordan, Maxim Makatchev, Maxim Makatchev, Kurt Vanlehn, Kurt Vanlehn
The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers via natural language. Although there are inexpensive techniques for...
Combining competing language understanding approaches in an intelligent tutoring system (2004)
Pamela W. Jordan, Maxim Makatchev, Kurt Vanlehn
Abstract. When implementing a tutoring system that attempts a deep understanding of students ’ natural language explanations, there are three basic approaches to choose between; symbolic, in which...
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
Abstract. The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers via natural language. Although there are inexpensive...
Pamela W. Jordan, Maxim Makatchev, Kurt Vanlehn
Abstract. The Why2-Atlas tutoring system presents students with qualitative physics
Pamela W. Jordan, Maxim Makatchev, Kurt Vanlehn
Abstract. The Why2-Atlas tutoring system presents students with qualitative physics
Abductive Proofs as Models of Students' Reasoning about Qualitative Physics (2004)
Maxim Makatchev, Pamela W. Jordan, Umarani Pappuswamy, Kurt Vanlehn
In this paper we describe a part of the Why2-Atlas tutoring system that models students' reasoning in the domain of qualitative physics. The main goals of the model are (1) to evaluate...
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive techniques...
Modeling Students' Reasoning about Qualitative Physics: Heuristics for Abductive Proof Search (2004)
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
We describe a theorem prover that is used in the Why2Atlas tutoring system for the purposes of evaluating the correctness of a student's essay and for guiding feedback to the student. The...
Abductive Theorem Proving for Analyzing (2004)
Student Explanations Pamela, Pamela W. Jordan, Maxim Makatchev, Kurt Vanlehn
The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers via natural language. Although there are inexpensive techniques for...
Abductive Proofs as Models of Students' Reasoning about Qualitative Physics (2004)
Maxim Makatchev, Pamela W. Jordan, Umarani Pappuswamy, Kurt Vanlehn
system that models students' reasoning in the domain of qualitative physics. The main goals of the model are (1) to evaluate correctness of the student's essay, and, in case the essay...
Combining competing language understanding approaches in an intelligent tutoring system (2004)
Pamela W. Jordan, Maxim Makatchev, Kurt Vanlehn
Abstract. When implementing a tutoring system that attempts a deep understanding of students ’ natural language explanations, there are three basic approaches to choose between; symbolic, in which...
Abductive proofs as models of students’ reasoning about qualitative physics (2004)
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
In this paper we describe a part of the Why2-Atlas tutoring system that models students ’ reasoning in the domain of qualitative physics. The main goals of the model are (1) to evaluate correctness...
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
Abstract. The Why2-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers through natural language. Although there are inexpensive...
Modeling students’ reasoning about qualitative physics: Heuristics for abductive proof search (2004)
Maxim Makatchev, Pamela W. Jordan, Kurt Vanlehn
Abstract. We describe a theorem prover that is used in the Why2-Atlas tutoring system for the purposes of evaluating the correctness of a student’s essay and for guiding feedback to the student....
DRAFT – do not cite or quote The Andes Physics Tutoring System: Lessons Learned (2004)
Kurt Vanlehn, Collin Lynch, Kay Schulze, Joel A. Shapiro, Robert Shelby, Linwood Taylor, ...
The Andes system is a mature intelligent tutoring system that has helped hundreds of students improve their learning of university physics. It replaces pencil and paper problem solving homework....
A hybrid text classification approach for analysis of student essays (2003)
Carolyn P. Rosé, Antonio Roque, Dumisizwe Bhembe, Kurt Vanlehn
We present CarmelTC, a novel hybrid text classification approach for analyzing essay answers to qualitative physics questions, which builds upon work presented in (Rosé et al., 2002a). CarmelTC...
A comparison of tutor and student behavior in speech versus text based tutoring (2003)
Carolyn P. Rosé, Diane Litman, Dumisizwe Bhembe, Kate Forbes, Scott Silliman, Ramesh Srivastava, ...
This paper describes preliminary work in exploring the relative effectiveness of speech versus text based tutoring. Most current tutorial dialogue systems are text based (Evens et
K.: Overcoming the Knowledge Engineering Bottleneck for Understanding Student Language Input (2003)
Carolyn P. Rosé, Andy Gaydos, Brian S. Hall, Antonio Roque, Kurt Vanlehn
Abstract. In this paper we present Carmel-Tools, a new set of authoring tools for overcoming the knowledge engineering bottleneck for building tutorial dialogue systems that can accept natural...
A comparison of tutor and student behavior in speech versus text based tutoring (2003)
Carolyn P. Rosé, Diane Litman, Dumisizwe Bhembe, Kate Forbes, Scott Silliman, Ramesh Srivastava, ...
This paper describes preliminary work in exploring the relative effectiveness of speech versus text based tutoring. Most current tutorial dialogue systems are text based (Evens et
Why do only some events cause learning during human tutoring (2003)
Kurt Vanlehn, Stephanie Siler, Charles Murray, Takashi Yamauchi, William B. Baggett
Developers of intelligent tutoring systems would like to know what human tutors do and which activities are responsible for their success in tutoring. We address these questions by comparing episodes...
K.: Overcoming the Knowledge Engineering Bottleneck for Understanding Student Language Input (2003)
Carolyn P. Rosé, Andy Gaydos, Brian S. Hall, Antonio Roque, Kurt Vanlehn
Abstract. In this paper we present Carmel-Tools, a new set of authoring tools for overcoming the knowledge engineering bottleneck for building tutorial dialogue systems that can accept natural...
Modelling hinting strategies for geometry theorem proving (2003)
Abstract. This study characterizes hinting strategies used by a human tutor to help students learn geometry theorem proving. Current tutoring systems for theorem proving provide hints that encourage...
Why do only some events cause learning during human tutoring (2003)
Kurt Vanlehn, Stephanie Siler, Charles Murray, Takashi Yamauchi, William B. Baggett
Developers of intelligent tutoring systems would like to know what human tutors do and which activities are responsible for their success in tutoring. We address these questions by comparing episodes...
VanLehn,Kurt, Brown,John Seely
At some time in our lives, we have all been forced to learn the procedural skills which supposedly comprise mathematical literacy (e.g., place value addition) through the process of rote...
Competitive Argumentation in Computational Theories of Cognition. (2002)
VanLehn,Kurt, Brown,John Seely, Greeno,James
Computer science has given psychology a new way of expressing models of cognition that is much more detailed and precise than its predecessors. But unfortunately, the increased detail and precision...
Using bayesian networks to manage uncertainty in student modeling (2002)
Cristina Conati, Abigail Gertner, Kurt Vanlehn
Abstract. When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it...
The architecture of Why2-Atlas: A coach for qualitative physics essay writing (2002)
Kurt Vanlehn, Pamela W. Jordan, Carolyn P. Rosé, Dumisizwe Bhembe, Michael Böttner, Andy Gaydos, ...
Abstract. The Why2-Atlas system teaches qualitative physics by having students write paragraph-long explanations of simple mechanical phenomena. The tutor uses deep syntactic analysis and abductive...
Discourse Processing for Explanatory Essays in Tutorial Applications (2002)
Pamela Jordan And, Pamela W. Jordan, Kurt Vanlehn
The Why-Atlas tutoring system presents students with qualitative physics questions and encourages them to explain their answers via natural language. Although there are inexpensive techniques for...
Using bayesian networks to manage uncertainty in student modeling (2002)
Cristina Conati, Abigail Gertner, Kurt Vanlehn
Abstract Modeling a student within an intelligent tutoring system involves inherent uncertainty. Even during the simplest tutorial interaction, it is hard to establish unequivocally what a student...
Intelligent tutoring systems with conversational dialogue (2001)
Arthur C. Graesser, Kurt Vanlehn, Carolyn P. Rosé, Pamela W. Jordan, Derek Harter
■ Many of the intelligent tutoring systems that have been developed during the last 20 years have proven to be quite successful, particularly in the domains of mathematics, science, and technology....
A decision-theoretic architecture for selecting tutorial discourse actions (2001)
R. Charles Murray, Kurt Vanlehn, Jack Mostow
We propose a decision-theoretic architecture for selecting tutorial discourse actions. DT Tutor, an action selection engine which embodies our approach, uses a dynamic decision network to consider...
A decisiontheoretic approach for selecting tutorial discourse actions (2001)
R. Charles Murray, Kurt Vanlehn
We propose a decision-theoretic architecture for selecting tutorial discourse actions. DT Tutor, an action selection engine which embodies our approach, uses a dynamic decision network to consider...
A comparative evaluation of socratic versus didactic tutoring (2001)
Carolyn Penstein Rosé, Johanna D. Moore, Kurt Vanlehn, David Allbritton
While the effectiveness of one-on-one human tutoring has been well established, a great deal of controversy surrounds the issue of which features of tutorial dialogue separate effective uses of...
Interactive conceptual tutoring in atlas-andes (2001)
Carolyn P. Ros'e, Pamela Jordan, Michael Ringenberg, Stephanie Siler, Kurt Vanlehn, Anders Weinstein
The goal of the Atlas project is to increase the opportunities for students to construct their own knowledge by conversing (in typed form) with a natural language-based ITS. Our previous research...
A Comparative Evaluation of Socratic versus Didactic Tutoring (2001)
Carolyn Penstein Rose, Johanna D. Moore, Kurt Vanlehn, David Allbritton
While the effectiveness of one-on-one human tutoring has been well established, a great deal of controversy surrounds the issue of which features of tutorial dialogue separate effective uses of...
Andes: An Intelligent Tutor for Classical Physics (2000)
Kay G. Schulze, Robert N. Shelby, Donald J. Treacy, Mary C. Wintersgill, Kurt Vanlehn, Abigail Gertner
Conati, Cristina, Vanlehn, Kurt
We present a computational framework designed to improve learning from examples by supporting self-explanation ö the process of clarifying and making more complete to oneself the solution of an...
Conati, Cristina, Vanlehn, Kurt
We present a computational framework designed to improve learning from examples by supporting self-explanation ö the process of clarifying and making more complete to oneself the solution of an...
We present a computational framework designed to improve learning from examples by supporting self-explanation – the process of clarifying and making more complete to oneself the solution of an...
DT Tutor: A decision-theoretic dynamic approach for optimal selection of tutorial actions (2000)
R. Charles Murray, Kurt Vanlehn
Abstract. DT Tutor uses a decision-theoretic approach to select tutorial actions for coached problem solving that are optimal given the tutor’s beliefs and objectives. It employs a model of...
We present further results on the educational effectiveness of an intelligent computer tutor that helps students learn effectively from examples by coaching self-explanation – the process of...
ITS Tools for Natural Language Dialogue: A Domain-Independent Parser and Planner (2000)
Reva Freedman Carolyn, Carolyn Penstein Rose, Michael A. Ringenberg, Kurt Vanlehn
The goal of the Atlas project is to increase the opportunities for students to construct their own knowledge by conversing (in typed form) with a natural language-based ITS. In this paper we describe...
International Journal of Artificial Intelligence in Education (2000), 11, 398-415 (2000)
this paper, we describe how these solutions have been implemented in a computer tutor that coaches self-explanation within Andes, a tutoring system for Newtonian physics. We also present the results...
DT Tutor: A decision-theoretic dynamic approach for optimal selection of tutorial actions (2000)
R. Charles Murray, Kurt Vanlehn
Abstract. DT Tutor uses a decision-theoretic approach to select tutorial actions for coached problem solving that are optimal given the tutor’s beliefs and objectives. It employs a model of...
A student model to assess self-explanation while learning from examples (1999)
Abstract. The SE-Coach is a tutoring system that supports students in applying the learning strategy known as self-explanation- the process of clarifying to oneself the solution of an example. In...
A student model to assess self-explanation while learning from examples (1999)
Abstract. The SE-Coach is a tutoring system that supports students in applying the learning strategy known as self-explanation- the process of clarifying to oneself the solution of an example. In...
A Student Model to Assess Self-Explanation while (1999)
Learning From Examples, Cristina Conati, Kurt Vanlehn
The SE-Coach is a tutoring system that supports students in applying the learning strategy known as self-explanation - the process of clarifying to oneself the solution of an example. In this paper,...
Towards a Theory of Impasse-Driven Learning. (1998)
Earlier work has shown that students often reach impasses while trying to use a procedural skill that they are acquiring. The step that they believe should be executed next cannot be performed. If...
Understanding Algebra Equation Solving Strategies. (1998)
A task analysis of linear algebraic equation solving is presented. The problem space is shown to have an elegant mathematical form. Several strategies for searching the problem space are delineated,...
Flexible Execution of Cognitive Procedures. (1998)
Several current theories of procedural knowledge hypothesize that procedures are organized as hierarchies of goals, wherein accomplishing a goal requires accomplishing all or some of its subgoals....
Cirrus: An Automated Protocol Analysis Tool. (1998)
Cirrus is a tool for protocol analysis. Given an encoded protocol of a subject solving problems, it constructs a modal that will produce the same protocol as the subject when it is applied to the...
Deriving Descriptions of the Mind. (1998)
Cirrus is a tool for protocol analysis. Given an encoded protocol of a subject solving problems, it constructs a model that will produce the same protocol as the subject when it is applied to the...
Changing the Layers of Mind. (1998)
It is common in cognitive science to assume that the mind is composed of layers of programmable machines. The machine of the top layer runs the end user program which, roughly speaking, performs the...
Theoretical work suggests that when students learn a complex skill, they may face ambiguities in how to interpret the training material, and that there may be social conventions, called felicity...
Kowalski, Bernadette, VanLehn, Kurt
In this paper, we discuss Cirrus, a semi-automated data analysis and model formation system. Cirrus starts with a half-order model for a data set, and induces the remaining knowledge necessary to...
Efficient Specialization of Relational Concepts. (1998)
An algorithm is presented for a common induction problem, the specialization of overly general concepts. A concept is too general when it matches a negative example. The particular case addressed...
Problem Solving and Cognitive Skill Acquisition. (1998)
There has been a great deal of work in human problem solving since the landmark publication of Newell and Simon's Human Problem Solving in 1972. After reviewing the 1972 theory and the subsequent...
A Version Space Approach to Learning Context-Free Grammars. (1998)
In principal, the version space approach can be applied to any induction problem. However, in some cases the representation language for generalizations is so powerful that 1) some of the update...
Discovering Problem Solving Strategies: What Humans Do and Machines Don't (Yet). (1998)
People can discover new problem solving strategies on their own, without help from a teacher, text or other source. Many machine learning programs exist that discover strategies under similar...
Learning Events in the Acquisition of Three Skills. (1998)
Current theories of cognitive skill acquisition, new problem solving rules are constructed by proceduralization, production compounding, chunking, syntactic generalization, and a variety of other...
Cirrus: Inducing Subject Models from Protocol Data. (1998)
Kowalski, Bernadette, VanLehn, Kurt
Cirrus is a system for aiding the analysis of protocol data. It assumes that subjects are following a non-deterministic procedure or plan, which is specified for it by the user. It uses machine...
Non-LIFO (Last-in-First-Out) Execution of Cognitive Procedures. (1998)
VanLehn, Kurt, Ball, William, Kowalski, Bernadette
Many current theories of human problem solving and skill acquisition assume that people work only on the unsatisfied goal that was created most recently. That is, the architecture obeys a...
Kowalski, Bernadette, VanLehn, Kurt
In this paper, we discuss Cirrus, a semi-automated data analysis and model formation system. Cirrus starts with a half-order model for a data set, and induces the remaining knowledge necessary to...
Theoretical work suggests that when students learn a complex skill, they may face ambiguities in how to interpret the training material, and that there may be social conventions, called felicity...
Problem Solving and Cognitive Skill Acquisition. (1998)
There has been a great deal of work in human problem solving since the landmark publication of Newell and Simon's Human Problem Solving in 1972. After reviewing the 1972 theory and the subsequent...
Non-LIFO Execution of Cognitive Procedures. (1998)
VanLehn, Kurt, Ball, William, Kowalski, Bernadette
Many current theories of human problem solving and skill acquisition assume that people work only on the unsatisfied goal that was created most recently. That is, the architecture obeys a...
Goal Reconstruction: How Teton Blends Situated Action and Planned Action. (1998)
This chapter discusses an extra capability that few cognitive architectures have, even though it is both useful from a programming point of view and arguably a good approximation to a human...
Cirrus: Inducing Subject Models from Protocol Data. (1998)
Kowalski, Bernadette, VanLehn, Kurt
Cirrus is a system for aiding the analysis of protocol data. It assumes that subjects are following a non-deterministic procedure or plan, which is specified for it by the user. It uses machine...
Explanation-Based Learning of Correctness: Towards a Model of the Self-Explanation Effect. (1998)
VanLehn, Kurt, Ball, William, Kowalski, Bernadette
Two major techniques in machine learning, explanation-based learning and explanation completion, are both superficially plausible models for Chi's self-explanation effect, wherein the amount of...
Two Pseudo-Students: Applications of Machine Learning to Formative Evaluation. (1998)
The goal of the research described here is to develop simulation programs that can be used for formative evaluation during the instructional design process. Such simulations are called...
Efficient Specialization of Relational Concepts. (1998)
This research note presents an algorithm for a common induction problem, the specialization of overly general concepts. A concept is too general when it matches a negative example. The particular...
A Version Space Approach to Learning Context-Free Grammars. (1998)
In principle, the version space approach can be applied to any induction problem. However, in some cases the representation language for generalizations is so powerful that (1) some of the update...
This chapter reviews the research literature concerned with the student modeling component of intelligent tutoring systems. An intelligent tutoring system, or ITS, is a computer program that...
Goal Reconstruction: How Teton Blends Situated Action and Planned Action. (1998)
This document discusses an extra capability that few cognitive architectures have, even though it is both useful from a programming point of view and arguably a good approximation to a human...
Rule Acquisition Events in the Discovery of Problem Solving Strategies. (1998)
Although there are many machine learning programs that can acquire new problem solving strategies, we do not know exactly how their processes will manifest themselves in human behavior, if at all. In...
Knowledge-Based Environments for Teaching and Learning. (1998)
Woolf, Beverly, Soloway, Elliot, Clancey, William, VanLehn, Kurt, Suthers, Dan
The Spring Symposium on Knowledge-based Environments for Teaching and Learning focused on the use of technology to facilitate learning, training, teaching, counseling, coaxing and coaching. Sixty...
Explanation-Based Learning of Correctness: Towards a Model of the Self-Explanation Effect. (1998)
VanLehn, Kurt, Ball, William, Kowalski, Bernadette
Two major techniques in machine learning, explanation-based learning and explanation completion, are both superficially plausible models for Chi's self-explanation effect, wherein the amount of...
Two Pseudo-Students: Applications of Machine Learning to Formative Evaluation. (1998)
The goal of the research described here is to develop simulation programs that can be used for formative evaluation during the instructional design process. Such simulations are called...
Architectures for Intelligence: The Twenty-Second Carnegie Symposium on Cognition. (1998)
This proposal requests funds to partially support a symposium on Architectures for Intelligence. The major purposes of the symposium are: (1) To promote interaction among researchers who are pursuing...
A Computation Model of Acquisition for Children's Addition Strategies. (1998)
Jones, Randolph M., VanLehn, Kurt
GIPS is a problem solving system that models the strategy shifts of children learning to add. The system uses a generalized form of means-ends analysis as its reasoning algorithm, and it learns...
Strategy Shifts Without Impasses: A Computational Model of the Sum-to-Min Transition. (1998)
Jones, Randolph M., VanLehn, Kurt
The SUM-to-MIN transition that children exhibit when learning to add provides an ideal domain for studying naturally occurring discovery processes. We discuss a computational model that accounts for...
Learning Physics Via Explanation-Based Learning of Correctness and Analogical Search Control, (1998)
VanLehn, Kurt, Jones, Randolph M.
Cascade models humans learning college physics by studying examples and solving problems. It simulates the main qualitative phenomena visible in human protocols of learning, including several...
Learning by Explaining Examples to Oneself: A Computational Model. (1998)
VanLehn, Kurt, Jones, Randolph M.
Several investigations have found that students learn more when they explain examples to themselves while studying them. Moreover, they refer less often to the examples while solving problems, and...
On-Line Assessment of Expertise, (1998)
VanLehn, Kurt, Chi, Michelene T., Glaser, Robert
Cognitive science has developed a number of experimental paradigms that appear promising as tools for assessing expertise. However, they typically involve verbal report data and much labor by human...
On-Line Assessment of Expertise. (1998)
There was one major objective during this report period, to develop the assessment techniques for the qualitative problem solving, problem classification, and difficulty estimation activities. As...
On-Line Assessment of Expertise. (1998)
There were two main objectives during this report period. The first was to extend Olae's physics rule base or cognitive domain model to include incorrect rules and correct but unusual rules. The...
On-Line Assessment of Expertise. (1998)
The main objective in this report period was to deal with the combinatorial explosion in the size of the belief networks needed to analyze regular problem solving behavior. As mentioned in our...
On-Line Assessment of Expertise. (1998)
In this period, we have continued the development of the assessment methods for the problem classification, qualitative problem solving, and difficulty estimation activities, whose design was...
Analysis of Symbolic Parameter Models. (1998)
Simon, Herbert A., Polk, Thad, Vanlehn, Kurt
Model-fitting, the problem of finding parameter settings that cause a model to fit given data as closely as possible, is a hard but important problem in cognitive science in general, and in cognitive...
This report describes progress toward constructing a unified, computer-based model of all the major phenomena in cognitive skill acquisition. An extensive review of the literature was completed and...
Procedural help in Andes: Generating hints using a Bayesian network student model (1998)
Abigail S. Gertner, Cristina Conati, Kurt Vanlehn
One of the most important problems for an intelligent tutoring system is deciding how to respond when a student asks for help. Responding cooperatively requires an understanding of both what solution...
Student modeling from conventional test data: A bayesian approach without priors (1998)
Kurt Vanlehn, Zhendong Niu, Stephanie Siler, Abigail Gertner
Abstract. Although conventional tests are often used for determining a student’s overall competence, they are seldom used for determining a finegrained model. However, this problem does arise...
Evaluation of an assessment system based on Bayesian student modeling (1998)
Abstract. Schools need assessments of students in order to make informed decisions. The most common assessments are tests consisting of questions or problems that can be answered in under a minute...
Procedural help in Andes: Generating hints using a Bayesian network student model (1998)
Abigail S. Gertner, Cristina Conati, Kurt Vanlehn
One of the most important problems for an intelligent tutoring system is deciding how to respond when a student asks for help. Responding cooperatively requires an understanding of both what solution...
Evaluation of an assessment system based on Bayesian student modeling (1998)
Kurt Vanlehn Learning, Kurt Vanlehn, Joel Martin
Schools need assessments of students in order to make informed decisions. The most common assessments are tests consisting of questions or problems that can be answered in under a minute each. When...
On-line student modeling for coached problem solving using Bayesian networks (1997)
Cristina Conati, Abigail S. Gertner, Kurt Vanlehn, Marek J. Druzdzel
Abstract. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES ’ student model uses a Bayesian network to do long-term knowledge...
On-line student modeling for coached problem solving using Bayesian networks (1997)
Cristina Conati, Abigail S. Gertner, Kurt Vanlehn, Marek J. Druzdzel
Abstract. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES ’ student model uses a Bayesian network to do long-term knowledge...
On-line student modeling for coached problem solving using Bayesian networks (1997)
Cristina Conati, Abigail S. Gertner, Kurt Vanlehn, Marek J. Druzdzel
Abstract. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES ’ student model uses a Bayesian network to do long-term knowledge...
On-line student modeling for coached problem solving using Bayesian networks (1997)
Cristina Conati, Abigail S. Gertner, Kurt Vanlehn, Marek J. Druzdzel
Abstract. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES ’ student model uses a Bayesian network to do long-term knowledge...
On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks (1997)
Cristina Conati, Abigail S. Gertner, Kurt Vanlehn
. This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES' student model uses a Bayesian network to do long-term knowledge...
A Computer Framework to Support Self-Explanation (1997)
Cristina Conati, Jill H. Larkin, Kurt Vanlehn
We present a computational framework for improving learning from examples by supporting self-explanation - the process of clarifying and making more complete to oneself the solution of an example....
Conceptual and meta learning during coached problem solving (1996)
Abstract. Coached problem solving is known to be e ective for teaching cognitive skills. Simple forms of coached problem solving are used in many ITS. This paper rst considers how university physics...
The paper presents POLA, a student modeling framework that performs probabilistic assessment of students ' performance while they solve problems in introductory Physics. Existing efforts toward...
Applications of Simulated Students: An Exploration (1996)
Kurt Vanlehn Stellan, Kurt Vanlehn, Stellan Ohlsson, Rod Nason
It is now possible to build machine learning systems whose behavior is consistent with data from human students. How can education use such simulated students? Applications that help three user...
Probabilistic Plan Recognition for Cognitive Apprenticeship (1996)
Interpreting the student's actions and inferring the student's solution plan during problem solving is one of the main challenges of tutoring basedon cognitive apprenticeship, especially in...
Conceptual and Meta Learning during Coached Problem Solving (1996)
. Coached problem solving is known to be effective for teaching cognitive skills. Simple forms of coached problem solving are used in many ITS. This paper first considers how university physics can...
Cognitive Skill Acquisition (1996)
Kurt Vanlehn Learning, Kurt Vanlehn
Cognitive skills acquisition is acquiring the ability to solve problems in intellectual tasks, where success is determined more by the subjects' knowledge than their physical prowess. This...
Probabilistic Plan Recognition for Cognitive Apprenticeship (1996)
Cristina Conati And, Cristina Conati, Kurt Vanlehn
Interpreting the student's actions and inferring the student's solution plan during problem solving is one of the main challenges of tutoring based on cognitive apprenticeship, especially...
Cognitive skill acquisition (1996)
Cognitive skills acquisition is acquiring the ability tosolve problems in intellectual tasks, where success is determined more by the subjects ' knowledge than their physical prowess. This...
The paper presents POLA, a student modeling framework that performs probabilistic assessment of students' performance while they solve problems in introductory Physics.
Student Assessment Using Bayesian Nets (1995)
This paper will focus exclusively on the problem solving activity. The other activities are described in Martin and VanLehn (1993, in press). This section describes OLAE's input (student...
Jones, Randolph M., Vanlehn, Kurt
When children learn to add, they count on their fingers, beginning with the simple Sum Strategy and gradually developing the more sophisticated and efficient Min strategy. The shift from Sum to Min...
What mediates the self-explanation effect? Knowledge gaps, schemas or analogies? (1993)
Kurt VanLehn, Randolph M. Jones
Several studies have found that learning is more effective when students explain examples to themselves. Although these studies show that learning and self-explanation co-occur, they do not reveal...
Better learners use analogical problem solving sparingly (1993)
Kurt Vanlehn, Randolph M. Jones
When solving homework exercises, human students often notice that the problem they are about to solve is similar to an example. They then deliberate over whether to refer to the example or to solve...
Learning by explaining examples to oneself: A computational model (1993)
Kurt VanLehn, Randolph M. Jones
Several investigations have found that students learn more when they explain examples to themselves while studying them. Moreover, they refer less often to the examples while solving problems, and...
Analyzing Completeness and Correctness of Utterances Using an ATMS
Analyzing coverage of a student's utterance or essay (completeness) and diagnosing errors (correctness) can be treated as a diagnosis problem and solved using a well-known technique for...