Deep Reasoning & Dialog Systems

Notes:

Deep reasoning is a type of artificial intelligence that involves using deep learning algorithms to enable a system to reason and make decisions based on complex and uncertain information. In the context of dialog systems, deep reasoning is used to enable the system to understand and respond to the user’s input in a more sophisticated and intelligent way. This may involve using deep learning algorithms to analyze the user’s input and generate a response that is relevant and appropriate to the conversation. Deep reasoning can help dialog systems to understand the user’s intent and provide more accurate and relevant responses, which can improve the overall quality and effectiveness of the conversation.

Resources:

Wikipedia:

Minimal recursion semantics (MRS)

References:

AutoTutor: An intelligent tutoring system with mixed-initiative dialogue AC Graesser, P Chipman, BC Haynes… – … , IEEE Transactions on, 2005 – ieeexplore.ieee.org … The largest learning gains have been on deep-reasoning mea- sures rather than measures of shallow knowledge. … 618 IEEE TRANSACTIONS ON EDUCATION, VOL. 48, NO. 4, NOVEMBER 2005 systems. And of course, the practical benefit is helping children and adults learn. … Cited by 362 Related articles All 4 versions

Correlations between dialogue acts and learning in spoken tutoring dialogues D Litman, K Forbes-Riley – Natural Language Engineering, 2006 – Cambridge Univ Press … 1 Introduction Research in tutorial dialogue systems is founded on the belief that a one-on-one natural language conversation with a tutor provides students with an environment that exhibits characteristics associated with learning. … Cited by 54 Related articles All 15 versions

Dialogue-learning correlations in spoken dialogue tutoring CK Looietal – … Learning Through Intelligent and Socially Informed …, 2005 – books.google.com … 2. Dialogue Data and Coding Schemes ITS POKE (Intelligent Tutoring SPOKEn dialogue system)[11] is a speech-enabled ver- sion of the text-based Why2-Atlas … This will allow us to test our hypothesis that student deep reasoning is more error-prone in the human-human corpus … Cited by 28 Related articles All 14 versions

AutoTutor: A Cognitive System That Simulates a Tutor Through Mixed-Initiative Dialogue AC Graesser, A Olney, BC Haynes… – … cognitive models in …, 2005 – books.google.com … It is informative to note that the largest learning gains from AutoTutor have been on deep reasoning measures, rather than measures of shallow knowledge. Auto- Tutor’s problems and dialogue facilities were designed to target deep rea- soning, so this result was quite expected. … Cited by 44 Related articles All 3 versions

Deeper natural language processing for evaluating student answers in intelligent tutoring systems V Rus, AC Graesser – Proceedings of the National Conference on Artificial …, 2006 – aaai.org … For intelligent tutorial dialogue systems, we show that en- tailment cases can be detected at various dialog turns during a tutoring session. … Students are encouraged to articulate lengthy an- swers that exhibit deep reasoning, rather than to recite small bits of shallow knowledge. … Cited by 25 Related articles All 5 versions

MIAMM—a multimodal dialogue system using haptics N Reithinger, D Fedeler, A Kumar, C Lauer… – … Dialogue Systems, 2005 – Springer … modality. For modalities like speech, no immediate feedback is necessary: you can use deep reasoning and react in the time span of about one second. … Page 6. 312 Advances in Natural Multimodal Dialogue Systems feedback. The … Cited by 26 Related articles All 12 versions

Detection of emotions during learning with AutoTutor AC Graesser, B McDaniel, P Chipman… – Proceedings of the 28th …, 2006 – Citeseer … The questions required answers that involved inferences and deep reasoning, such as why, how, what-if, what if not, how is X similar to Y?. Although each question required 3-7 sentences in an ideal answer, learners … ITSPOKE: An intelligent tutoring spoken dialogue system. … Cited by 100 Related articles All 5 versions

Detecting certainness in spoken tutorial dialogues J Liscombe, JB Hirschberg, JJ Venditti – 2005 – academiccommons.columbia.edu … of human-human spoken dialogues collected for the development of ITSPOKE, an intelligent tu- toring spoken dialogue system in the … Finally, the tutor more frequently utilizes deep reasoning type questions (DeepAnsQ) when the student is certain; whereas, he asks surface … Cited by 85 Related articles All 20 versions

Exploring affect-context dependencies for adaptive system development K Forbes-Riley, M Rotaru, DJ Litman… – … Technologies 2007: The …, 2007 – dl.acm.org … Identification and analysis of these depen- dencies is our first step in developing an adaptive version of our dialogue system. … We hypothesize that LAQs and DAQs are associated with more uncertainty because they are harder questions requiring definitions or deep reasoning. … Cited by 14 Related articles All 18 versions

The generalized intelligent framework for tutoring (GIFT) RA Sottilare, KW Brawner, BS Goldberg, HK Holden – 2012 – litelab.arl.army.mil … importance of questioning (Dillon, 1988) • relation between deep reasoning questions and … Fourteen facts about human tutoring: Food for thought for ITS developers. AI-ED 2003 Workshop Proceedings on Tutorial Dialogue Systems: With a View Toward the Classroom (pp. … Cited by 67 Related articles All 5 versions

Deep Reasoning in Clarification Dialogues with Mobile Robots H Coelho – ECAI 2010: 19th European Conference on Artificial …, 2010 – books.google.com … This makes the latter more constructive, valuable and helpful—characteristics still problematic in the area of human-robot dialogue systems at large. Page 212. 182 C. Jian et al./Deep Reasoning in Clarification Dialogues with Mobile Robots Furthermore, we have also treated … Cited by 4 Related articles All 4 versions

Modeling confusion: facial expression, task, and discourse in task-oriented tutorial dialogue JF Grafsgaard, KE Boyer, R Phillips… – Artificial Intelligence in …, 2011 – Springer … 99 dialogue systems can leverage these contextual models of student affect to inform such behaviors as question asking and adaptive delivery of … questions is consistent with a prior observation that the non-expert tutors in this corpus rarely posed deep reasoning questions, but … Cited by 8 Related articles All 11 versions

Qualitative spatial modelling of human route instructions to mobile robots H Shi, C Jian, B Krieg-Bruckner – Advances in Computer- …, 2010 – ieeexplore.ieee.org … that applying additional mechanisms in the reasoning process, in our case the deep reasoning and the deep reasoning with backtracking … The integration of the Conceptual Route Graph with its reasoning mechanisms into a dialogue system developed in our research center is … Cited by 7 Related articles All 7 versions

Lessons learned from virtual humans W Swartout – AI Magazine, 2010 – aaai.org Page 1. The Institute for Creative Technologies was founded a decade ago to bring together researchers working at the cutting edge of simulation technologies, such as comput- er graphics, artificial intelligence, and virtual reality … Cited by 26 Related articles All 5 versions

Rimac: A Natural-Language Dialogue System that Engages Students in Deep Reasoning Dialogues about Physics. S Katz, P Jordan, D Litman – Society for Research on Educational …, 2011 – ERIC Recent studies have shown that US students lag behind students in other developed countries in math and science (eg., Glod, 2007). Because one-on-one tutoring has proven to be a highly effective form of instruction (eg, Bloom, 1984; Cohen, Kulik, & Kulik, 1982; … Cited by 1 Related articles All 5 versions

An Evaluation of a Hybrid Language Understanding Approach for Robust Selection of Tutoring Goals. CP Rosé, K VanLehn – IJ Artificial Intelligence in Education, 2005 – cs.cmu.edu … These evaluations of recent tutorial dialogue systems demonstrate that the secret to achieving the same effectiveness of expert tutorial … Open-ended problems requiring deep reasoning and explanation go far beyond computational skills and provide deep insight into student … Cited by 23 Related articles All 14 versions

SNAP: An action-based ontology for e-commerce reasoning L Morgenstern, D Riecken – … Meet Industry, Proceedings of the 1st …, 2005 – researchgate.net … (Other parts included the implementation and the integration with a dialogue system; see [10]). … 5For example, the metrics of precision and recall are very important for Information Extraction but not particularly relevant for applications requiring deep reasoning; thus, a method of … Cited by 12 Related articles All 4 versions

Logic, self-awareness and self-improvement: The metacognitive loop and the problem of brittleness ML Anderson, DR Perlis – Journal of Logic and Computation, 2005 – Oxford Univ Press … MCL must be kept simple and fast; it is not aimed at clever tricks or deep reasoning. … Whereas the original TRAINS-96 dialogue system [3] would respond to this apparently contradictory sequence of commands by sending the very same train, our enhanced HCI system notes the … Cited by 76 Related articles All 15 versions

AutoTutor and Family: A Review of 17 Years of Natural Language Tutoring BD Nye, AC Graesser, X Hu – … Journal of Artificial Intelligence in Education, 2014 – Springer … The latter findings include the effectiveness of deep reasoning questions for tutoring multiple domains, of adapting to the affect of low-knowledge learners, of content over surface features … Using a domain-independent reactive planner to implement a medical dialogue system. … Cited by 17 Related articles All 3 versions

Design of Dialog-Based Intelligent Tutoring Systems to Simulate Human-to-Human Tutoring S D’Mello, A Graesser – Where Humans Meet Machines, 2013 – Springer … are conversationally smooth. We move beyond the basic AutoTutor system to novel dialog systems that model and respond to emotions and disengagement behaviors in addition to knowledge levels. These include systems … Cited by 4 Related articles All 3 versions

Conversational agents can provide formative assessment, constructive learning, and adaptive instruction AC Graesser, B McDaniel – The future of assessment: Shaping …, 2008 – 141.225.218.248 … The development of these dialogue systems would never have occurred without important technical breakthroughs in the fields of computational linguistics … AutoTutor was built to facilitate deep reasoning, and this was apparent in the effect sizes for deep multiple-choice … Cited by 4 Related articles

Deep-reasoning-centred Dialogue D Field, A Ramsay – Proceedings of the Eleventh European Workshop on …, 2007 – dl.acm.org … The system’s epistemic theorem prover does deep reasoning over its understanding of and beliefs about what the user has said (expressed as logical … Enabling a dialogue system to handle conversations in which users say things they do not believe is work we have in mind for … Cited by 1 Related articles All 14 versions

Reformulating student contributions in tutorial dialogue P Jordan, S Katz, P Albacete, M Ford… – Proceedings of the …, 2012 – dl.acm.org … will then outline our plans for implementing certain types of reformulation by first describing the current tutorial dialogue system and the … The students first solved a problem using the Andes system and afterwards they were presented with a deep-reasoning reflection question … Cited by 4 Related articles All 12 versions

Passively classifying student mood and performance within intelligent tutors RA Sottilare, M Proctor – Journal of Educational Technology & Society, 2012 – JSTOR … Stronger students ask fewer questions, but these questions tend to be “deep-reasoning questions” (Person & Graesser, 2003). … Mizoguchi, H. Pain, F. Verdejo, & K. Yacef (Eds.), Artificial Intelligence in Education 2003 Workshop Proceedings on Tutorial Dialogue Systems: With a … Cited by 22 Related articles All 17 versions

Planning-Based Models of Natural Language Generation K Garoufi – Language and Linguistics Compass, 2014 – Wiley Online Library … Such a system may also be part of a larger spoken dialog system that is designed to engage in a two-way interactive communication … Because this line of work involves deep reasoning about the beliefs, desires, and intentions (BDI) of agents participating in dialog, it is known as … Cited by 3 Related articles All 2 versions

Does it really matter whether students’ contributions are spoken versus typed in an intelligent tutoring system with natural language? SK D’Mello, N Dowell, A Graesser – Journal of Experimental …, 2011 – psycnet.apa.org There is the question of whether learning differs when students speak versus type their responses when interacting with intelligent tutoring systems with natural language dialogues … Cited by 19 Related articles All 7 versions

Context-aware speech recognition in a robot navigation scenario M Hacker – Proceedings of the 2nd Workshop on Context Aware …, 2012 – Citeseer … We are convinced that a richer context model and an advanced user model that allows deep reasoning over multiple dialogue turns … 2007) 5. Hacker, M., Elsweiler, D., Ludwig, B.: Investigating human speech processing as a model for spoken dialogue systems: An experimental … Cited by 3 Related articles All 4 versions

Developmental differences in self-regulated learning and question asking during learning with hypermedia J Sullins, R Azevedo – Proceedings of the 29th Annual …, 2007 – csjarchive.cogsci.rpi.edu … developing a conceptual framework for the understanding of self- and external- regulated learning, and (2) Building dialogue systems for adaptive … In addition, analysis revealed that there was a significant difference in the amount of deep-reasoning questions asked between the … Cited by 1 Related articles

BEETLE II: Deep natural language understanding and automatic feedback generation for intelligent tutoring in basic electricity and electronics M Dzikovska, N Steinhauser, E Farrow, J Moore… – International Journal of …, 2014 – Springer … Effective teaching methods rely on engaging the student in active experimentation and encouraging deep reasoning, often through the use of self … tutoring systems that use simulation as a training tool (eg de Jong and van Joolingen 1998) and tutorial dialogue systems that ask … Cited by 5 Related articles All 5 versions

Illustrations or Graphs: Some Students Benefit from One over the Other M Lipschultz, D Litman – Artificial Intelligence in Education, 2013 – Springer … language. Behavior Research Methods 36(2), 180–192 (2004) 6. Katz, S., Jordan, P., Litman, D., The Rimac Project Team: Rimac: A natural- language dialogue system that engages students in deep reasoning. SREE (2011 … Cited by 1 Related articles All 6 versions

Resolving conceptual mode confusion with qualitative spatial knowledge in human-robot interaction C Jian, H Shi – Spatial Information Theory, 2013 – Springer … model and the model-based computational framework into a natural language interactive dialogue system for navigating a mobile robot in indoor environments. Regarding the high-level strategies, especially how to combine and apply the deep reasoning with backtracking and … Cited by 1 Related articles All 4 versions

Virtual Learning Environments and Intelligent Tutoring Systems Survey of current approaches and design methodologies K Muñoz, P Mc Kevitt, T Lunney, J Noguez – Review Paper available from: … – karlamunoz.net … and tutor. Questions confirming the validity of the student knowledge are predominant. Deep-reasoning questions are predominant in high-quality students. Answers are used to assess the student’s understanding. Examples … Cited by 2 Related articles

Dialogue Systems in Education S Janarthanam – sites.google.com … Page 12. Tutorial Dialogue Systems • TDS = ITS + SDS • Tutoring modality = Socratic dialogue … Students in AutoTutor condition performed better than other two condition students for deep reasoning questions. • For shallow questions, no difference was seen. 6/17/2009 20 … Related articles

Modeling Student Benefit from Illustrations and Graphs M Lipschultz, D Litman – Intelligent Tutoring Systems, 2014 – Springer … Computer Speech & Language (2011) 7. Katz, S., Jordan, P., Litman, D., The Rimac Project Team: Rimac: A natural- language dialogue system that engages students in deep reasoning (2011) 8. Kohl, PB, Finkelstein, ND: Student representational competence and self … Related articles All 4 versions

AutoTutor: An Intelligent Tutoring System with Mixed-initiative Dialogue Arthur C. Graesser, Patrick Chipman, Brian C. Haynes, and Andrew Olney University of … A Graesser – 141.225.218.248 … AutoTutor [15]. The largest learning gains have been on deep reasoning measures Page 12. 12 … Therefore, tutoring is an ideal test bed for R&D on natural language dialogue systems. And of course, there is also the practical benefit of helping children and adults learn. Page 19. … Related articles

The nature of dialog: structural and lexical markers of dialogic teacher/learner interactions S Feller – Proceedings of the Workshop at SIGGRAPH Asia, 2012 – dl.acm.org … To sum up, a dialogic classroom setting is an adequate means to facilitate self-regulated learning and deep reasoning in the learner. … has already begun to implement important aspects of dialog into some of its applications including cultural models for dialog systems that are … Related articles

Natural Language Processing I Gurevych, D Bernhard – anthology.aclweb.org Page 1. Coling 2008: Educational Natural Language Processing – T utorial notes Manchester, August 2008 Educational Natural Language Processing Tutorial at COLING’08 Iryna Gurevych, Delphine Bernhard Educational Natural Language Processing … All 5 versions

Natural Language, Discourse, and Conversational Dialogues within Intelligent Tutoring Systems: A Review K Brawner, A Graesser – Design Recommendations for Intelligent …, 2014 – books.google.com … The TRADEM project uses content-based instruction in combination with dialogues and deep reasoning questions, built from the content automatically. … Paper presented at the Building Dialogue Systems for Tutorial Applications, Papers of the 2000 AAAI Fall Symposium. … Cited by 3 Related articles All 7 versions

[BOOK] ECAI 2010: 19th European Conference on Artificial Intelligence, 16-20 August 2010, Lisbon, Portugal: Including Prestigious Applications of Artificial … H Coelho – 2010 – books.google.com … Robotics & Autonomous Systems Deep Reasoning in Clarification Dialogues with Mobile Robots Cui Jian, Desislava Zhekova, Hui Shi and John Bateman Stream-Based Reasoning Support for Autonomous Systems Fredrik Heintz, Jonas Kvarnström and Patrick Doherty 79 85 …

Coherence Across Components in Cognitive Systems–One Ontology to Rule Them All G Behnke, D Ponomaryov, M Schiller, P Bercher… – uni-ulm.de … One key aspect of state-of-the-art dialog systems is the ability to individualize the ongoing dialog according to the user’s needs, requirements … It does not allow a deep reasoning about these tasks and their decompositions or other properties, which is possible with our approach. … Cited by 3 Related articles All 2 versions

Integrating A QA System With Dialogue Management For The Music Domain Z Xingtao – inf.ed.ac.uk … The idea is to dynamically change the dialogue strategy and the actions of a dialogue system based on optimising some kinds of rewards or costs, given the current state. … techniques to achieve deep reasoning capabilities and reliably accurate performance. … Related articles All 6 versions

Dialogic knowledge building in learning communities S Feller – Dialogue in Multilingual and Multimodal Communities, 2015 – books.google.com … In this chapter, I argue that learning communities foster these skills and thus provide a strong foundation for deep learning; ie learning that is based on deep reasoning and active knowledge building as defined by Krathwohl (2002), Chi and Ohlsson (2005) and Sfard (2001). …

Toward a model of intelligence in pedagogical agents M Ashoori, C Miao, ES Goh – 2009 – Citeseer … This group also developed an- other agent, PACO, to integrate ITS and collaborative dialogue systems. … Students are encouraged to articulate lengthy answers that exhibit deep reasoning, rather than to recite small bits of shallow knowledge. Page 13. Figure 22. … Cited by 2 Related articles All 2 versions

Predicting Changes in Level of Abstraction in Tutor Responses to Students. M Lipschultz, DJ Litman, PW Jordan, S Katz – FLAIRS Conference, 2011 – Citeseer … talking;” hence the nickname for Rimac: “talking river.” We thus considered Rimac to be well- suited to a dialogue system embedded in … After completing the problem, students in the HF con- dition were presented with a deep-reasoning reflection ques- tion which they needed to … Cited by 3 Related articles All 7 versions

AutoTutor and affective AutoTutor: Learning by talking with cognitively and emotionally intelligent computers that talk back S D’mello, A Graesser – ACM Transactions on Interactive Intelligent …, 2012 – dl.acm.org … AutoTutor’s tutorial ses- sions are typically geared to promote conceptual thinking and deep reasoning rather than memorization of definitions and facts. However, there is nothing in its design to prevent AutoTutor from helping students with the acquisition of domain-specific … Cited by 56 Related articles All 4 versions

Predicting semantic changes in abstraction in tutor responses to students M Lipschultz, D Litman, S Katz… – … Journal of Learning …, 2014 – inderscienceonline.com … Research into emotion detection in tutorial dialogue systems found that dialogue context information, such as the number of main … After completing the problem, students in the human feedback condition were presented with several deep-reasoning, ‘reflection questions’, which … Cited by 1 Related articles All 6 versions

A Review of Student Models Used in Intelligent Tutoring Systems PI Pavlik Jr, K Brawner, A Olney… – … for intelligent tutoring …, 2013 – eduworks.com … A common strategy is the so-called five-step dialogue frame (Graesser & Person, 1994; Graesser et al., 1995; Person et al., 1994):(1) Tutor asks a deep reasoning question,(2) Student gives an answer,(3) Tutor gives immediate feedback or pumps the student,(4) Tutor and … Cited by 5 Related articles All 8 versions

Toward spoken human–computer tutorial dialogues SK D’Mello, A Graesser, B King – Human–Computer Interaction, 2010 – Taylor & Francis … It is conceivable that ASR errors are less problematic in spoken dialogue systems if the content of the user’s utterance (response) can be linked to an appropriate tutor action. … In Proceedings of the Workshop on Tutorial Dialogue Systems: With a View toward the Classroom. … Cited by 30 Related articles All 5 versions

Tutoring Systems PI Pavlik Jr, K Brawner, A Olney… – … for Intelligent Tutoring …, 2013 – books.google.com … A common strategy is the so-called five-step dialogue frame (Graesser & Person, 1994; Graesser et al., 1995; Person et al., 1994):(1) Tutor asks a deep reasoning question,(2) Student gives an answer,(3) Tutor gives immediate feedback or pumps the student,(4) Tutor and … Cited by 1 Related articles

22nd International Conference on Computational Linguistics I Gurevych, D Bernhard – 2008 – aclweb.org … Educational applications are particularly challenging for NLP since they require an adaptation and practical application of NLP techniques to various types of discourse, eg tutoring dialogues which are different from typical task-oriented spoken dialogue systems. … All 7 versions

Fundamentals of Adaptive Intelligent Tutoring Systems for Self-Regulated Learning RA Sottilare – 2015 – DTIC Document … Facts about human tutoring (Person and Graesser 2003) • Importance of questioning (Dillon 1988) • Relation between deep reasoning questions and exam scores (Graesser and Person 1994) • Politeness strategies (Person et al. 1995) … Related articles All 2 versions

[BOOK] Modelling solution step discussions in tutorial dialogue M Buckley – 2011 – coli.uni-saarland.de … 19 2.2.2 Belief and knowledge states in tutorial dialogue . . . . . 20 2.3 Tutorial dialogue systems . . . . . … 96 6 Predicting the tutor’s task-level grounding actions 99 6.1 Machine learning and dialogue systems research . . . . . 100 … Cited by 1 Related articles

Web-based Artificial Intelligence Agents SC Patel, E Karanja, SK Maheshwari – dias.ac.in … The Natural Language Assistant (NLA) is a web-based natural language dialog system that helps users to find relevant products on e-commerce … Auto Tutor generates deep reasoning questions, and prompts students for answers, while also offering pointers through dialogue. … Related articles

Conversational Informatics and Human-Centered Web Intelligence. T Nishida – IEEE Intelligent Informatics Bulletin, 2007 – comp.hkbu.edu.hk … emphasis on the measuring nonverbal behaviors using the state-of-the-art sensing devices such as motion capture devices or eye trackers, rather than employing deep reasoning or planning … They originate from synthetic characters and natural language dialogue systems. … Cited by 2 Related articles All 13 versions

[BOOK] Learner answer assessment in intelligent tutoring systems RD Nielsen – 2007 – books.google.com Page 1. LEARNER ANSWER ASSESSMENT IN INTELLIGENT TUTORING SYSTEMS by RODNEY D. NIELSEN MS, University of Colorado, Boulder, 2005 A thesis submitted to the Faculty of the Graduate School of the University … Cited by 1 Related articles All 8 versions

Adaptive Intelligent Tutoring System (ITS) Research in Support of the Army Learning Model—Research Outline RA Sottilare – gifttutoring.org … Relationship between deep reasoning questions and exam scores (Graesser and Person, 1994). • Politeness strategies of tutors (Person et al., 1995). … AI-ED 2003 Workshop Proceedings on Tutorial Dialogue Systems: With a View Toward the Classroom (pp. 335–344). … Related articles All 6 versions

Computational Models Of Etiquette And Culture PE Wu, CA MillEr, HA FunK… – Human-Computer Etiquette …, 2010 – books.google.com … examples of its application. 4.4 Examples of Computational Models of Etiquette Some of the earliest computational applications of politeness in com- puter science literature can be found in dialog systems. pautler (1998) developed … Related articles All 2 versions

Using student mood and task performance to train classifier algorithms to select effective coaching strategies within Intelligent Tutoring Systems (ITS) RA Sottilare – 2009 – purl.fcla.edu … provides additional learning opportunities for weaker students. Good students ask fewer questions, but these questions tend to be “deep-reasoning questions” (Person & Graesser, 2003). Loftin, et al (2004) assert that “while one-to-one human tutoring is still superior to ITS in … Cited by 6 Related articles All 5 versions

A taxonomy of strategies for multimodal persuasive message generation M Guerini, O Stock, M Zancanaro – Applied Artificial Intelligence, 2007 – Taylor & Francis … technologies. Captology provides hardwired persuasive features while, on the contrary, our approach focuses on deep-reasoning capabilities that will make human-computer interfaces able to use persuasive communication with users. … Cited by 15 Related articles All 3 versions

Does It Really Matter Whether Students’ Contributions Are Spoken versus Typed in an Intelligent Tutoring System With Natural Language? SK D’Mello, N Dowell, A Graesser – academia.edu … The 4-alternative multiple-choice format was designed to assess deep levels of knowledge. The questions required answers that involved inferences and deep reasoning, such as why, how, what-if, what if not, how is X similar to Y?. These questions that assess deep levels of … Related articles

Collaborative Research: Improving Science Learning in Inquiry-based Programs W Ward, R Cole – bltek.com … We refer to this initial version of MyST as MyST-SDS (Spoken Dialog System), since students spent nearly the entire tutoring session conversing with Marni. … Page 8. 8 1. My Science Tutor—Spoken Dialog System (MyST- SDS) The MyST Vision: A Virtual Tutor for Every Child … Related articles All 4 versions

Adaptive Tutoring for Self-Regulated Learning: A Tutorial on Tutoring Systems RA Sottilare, AM Sinatra – researchgate.net Page 1. Adaptive Tutoring for Self-Regulated Learning: A Tutorial on Tutoring Systems by Robert A Sottilare and Anne M Sinatra ARL-SR-0305 December 2014 Approved for public release; distribution is unlimited. Page 2. NOTICES Disclaimers … Related articles

Detecting naturalistic expressions of nonbasic affect using physiological signals O AlZoubi, SKD Mello, R Calvo – Affective Computing, IEEE …, 2012 – ieeexplore.ieee.org … Auto- Tutor’s dialogues are organized around difficult ques- tions, such as why, how, what-if, what if not, and how is X similar to Y. These questions require answers involving inferences, explanations, and deep reasoning. Although … Cited by 21 Related articles All 7 versions

Learning to troubleshoot: Multistrategy learning of diagnostic knowledge for a real-word problem solving task A Ram, S Narayanan, MT Cox – cc.gatech.edu … Recent research in diagnostic problem solving has proposed the use of “deep” reasoning methods (Davis, 1985) … system is very simple since that was not the focus of our research; however, it would be relatively easy to include a more sophisticated dialog system if desired. . … Related articles All 10 versions

Research, Teaching, and Community for the New Decade H Varotto – LINKS, 2010 – cs.pitt.edu … NSF Litman An Affect-Adaptive Spoken Dialogue System that Responds Based on User Model and Multiple Affect States NSF Litman Improving a Natural-Language Tutoring System that Engages Students in Deep Reasoning Dialogues About Physics NSF … Related articles All 7 versions

A Pragmatic Approach to Computational Narrative Understanding E Tomai – 2009 – qrg.northwestern.edu … EA NLU is evaluated through a series of experiments with two cognitive models, showing that it is capable of meeting the deep reasoning requirements those models pose, and that the constraints provided by the models can effectively guide the interpretation process. … Related

Automated explanation of research informed consent by embodied conversational agents R Fernando – 2009 – iris.lib.neu.edu … AutoTutor generally presents deep reasoning questions to learners and uses a variety of conversational moves to elicit the correct response from the learner. … AutoTutor’s tutorial dialogue is driven by a curriculum script, with a topic for each major deep reasoning question. … Cited by 2 Related articles All 6 versions

MENON: automating a Socratic teaching model for mathematical proofs D Tsovaltzi – 2010 – scidok.sulb.uni-saarland.de … 34 1.2.6 Theoretical Work on Designing Feedback Strategies . . . 35 1.2.7 Dialogue Systems: Discourse vs. Task Planning . . . . . … Page 22. xxii CONTENTS Page 23. xxiii List of Figures 1.1 The architecture of the prototype NL tutorial dialogue system of the Dialog project . . . . . … Cited by 1 Related articles All 2 versions

The ASSISTments Ecosystem: Building a platform that brings scientists and teachers together for minimally invasive research on human learning and teaching NT Heffernan, CL Heffernan – … Journal of Artificial Intelligence in Education, 2014 – Springer … 2005 ), ASSISTments has evolved, in some respects, to be the antithesis of an AIED system. There is not a strong “student model” as recommended by Woolf ( 2009 ), nor does the system do any deep reasoning that some might expect of an “intelligent” tutoring system. … Cited by 21 Related articles All 2 versions

Pre-Processing MRSes T Bruland – In Proceedings of the 10th International Conference on …, 2013 – aclweb.org … ACE can parse and generate using the compiled grammar. Our goal is to create a pipeline for the NorSource grammar and use it to create small question-answer systems or dialogue systems. The first step in the pipeline is the parsing process with ACE. … Cited by 1 Related articles All 9 versions

Speaking with computers: a bottom-up approach F LEFEVRE – lia.univ-avignon.fr … This task is a different genre of dialogue which shares features with tutorial dialogue systems (see below). … The learner’s answer can be lengthy, exhibiting deep reasoning and thus requiring elaborate processing to interpret it correctly. … Related articles All 3 versions

Scaffolding Made Visible AM Olney – Design Recommendations for Intelligent Tutoring …, 2014 – books.google.com … com/doi/pdf/10.1207/s15327809jls1303_6 Person, NK & Graesser, AC (2003). Fourteen facts about human tutoring: Food for thought for ITS developers. In AIED 2003 Workshop Proceedings on Tutorial Dialogue Systems: With a view toward the classroom (pp. 335-344). … Related articles All 7 versions

Interactive generation of effective discourse in situated context: a planning-based approach K Garoufi – 2013 – opus.kobv.de … practical (Allen et al., 2001). Interactive language generation is a key capability of spoken dialog systems, which are aimed at two-way spoken commu- Page 26. 1.2. Challenges 4 nication with a user. Such systems typically augment … Cited by 1 Related articles All 4 versions

Interacting with Philosophy Through Natural Language Conversation W XUAN – 2013 – scholarbank.nus.edu.sg Page 1. INTERACTING WITH PHILOSOPHY THROUGH NATURAL LANGUAGE CONVERSATION WANG XUAN B.Eng.(Hons.), NUS A THESIS SUBMITTED FOR THE DEGREE OF DOCTOR OF PHILOSOPHY NUS GRADUATE SCHOOL FOR INTEGRATIVE … Related articles All 2 versions

Defining Tailored Training Approaches for Army Institutional Training PS Schaefer, JL Dyer – 2013 – DTIC Document Page 1. Research Report 1965 Defining Tailored Training Approaches for Army Institutional Training Peter S. Schaefer and Jean L. Dyer US Army Research Institute March 2013 United States Army Research Institute for the Behavioral and Social Sciences … Cited by 1 Related articles All 2 versions

Intelligent Informatics P Chan, R Menezes, D Mitra, E Ribeiro, M Silaghi… – 2007 – comp.hkbu.edu.hk Page 1. THE IEEE Intelligent Informatics BULLETIN IEEE Computer Society Technical Committee November 2007 Vol. 8 No. 1 (ISSN 1727-5997) on Intelligent Informatics ————— … Related articles All 4 versions