This paper presents a robust methodology for grounding vocabulary in robots. A social language grounding experiment is designed, where, a human instructor teaches a robotic agent the names of the objects present in a visually shared environment. Any system for grounding vocabulary has to incorporate the properties of gradual evolution and lifelong learning. The learning model of the robot is adopted from an ongoing work on developing systems that conform to these properties. Significant modifications have been introduced to the adopted model, especially to handle words with multiple meanings. A novel classification strategy has been developed for improving the performance of each classifier for each learned category. A set of six new nearest-neighbor based classifiers have also been integrated into the agent architecture. A series of experiments were conducted to test the performance of the new model on vocabulary acquisition. The robot was shown to be robust at acquiring vocabulary and has the potential to learn a far greater number of words (with either single or multiple meanings).

We propose a collaborative approach to the issue of resource creation for commonsense computing by developing a collaboratory application aimed at children. Human validation is enabled through a game-with-a-purpose (GWAP) interface, gathering reliability judgements of assertions that can be used to aid the process of resource validation. Our experiments confirm that children aged 10 to 12 can be valuable and reliable partners in building commonsense databases, due to their stage of mental development and their eagerness to play GWAPs. Results show that children adapt their word choice in the assertions they provide to the difficulty level of the stimuli words, and that the judgements gathered through in-game validation can help to validate about 30% of the gathered statements automatically.

This paper presents our work in developing a commonsense knowledge source based on semantic concepts about objects, activities and their relationships in a child’s daily life. This commonsense ontology is then used by our automatic story generator to output children's stories of the fable form from a given input picture. The generated story is a narration of the events of a basic plot that flows from negative to positive (rule violation to value acquisition), using themes that are familiar to children. The paper ends with descriptions of further investigations that are underway to extend the system, including using a formal upper ontology to represent storytelling knowledge, and the generation of stories from a given set of sequential scenes.

We present CrossBridge, a practical algorithm for retrieving analogies in large, sparse semantic networks. Other algorithms adopt a generate-and-test approach, retrieving candidate analogies by superficial similarity of concepts, then testing them for the particular relations involved in the analogy. CrossBridge adopts a global approach. It organizes the entire knowledge space at once, as a matrix of small concept-and-relation subgraph patterns versus actual occurrences of subgraphs from the knowledge base. It uses the familiar mathematics of dimensionality reduction to reorganize this space along dimensions representing approximate semantic similarity of these subgraphs. Analogies can then be retrieved by simple nearest-neighbor comparison. CrossBridge also takes into account not only knowledge directly related to the source and target domains, but also a large background Commonsense knowledge base. Commonsense influences the mapping between domains, preserving important relations while ignoring others. This property allows CrossBridge to find more intuitive and extensible analogies. We compare our approach with an implementation of structure mapping and show that our algorithm consistently finds analogies in cases where structure mapping fails. We also present some discovered analogies.

In order to understand the role of metacognition and self-regulation in student learning, 35 college students were asked to solve problems in college linear algebra and in remedial math using Cognitive Constructor. Results reveal the predominance of forward chaining in problem solving.

A seminal study conducted by Greene, Bolick, and Robertson (2010) showed that learners do not always engage in appropriate metacognitive and self-regulatory processes while learning about history. However, little research exists to guide the design of technology-rich learning environments (TRLEs) as metacognitive tools in social sciences education. In order to address this issue, we designed a metacognitive tool using a bottom-up approach (Poitras, 2010; Poitras, Lajoie, & Hong, in prep). Thirty-two undergraduate students read an historical narrative text either with or without the benefit of the metacognitive tool. Results from process and product data suggest that learners had better recall because the metacognitive tool assisted learners to (a) notice that particular events are unexplained in the circumstances described in an historical narrative text, and (b) generate hypothetical causes to explain the occurrence of such events. We discuss the implications of these findings for the development of the MetaHistoReasoning Tool, a TRLE that assists learners’ historical reasoning while they accomplish authentic tasks of historical inquiry.

A well-documented finding in the help-seeking literature is that especially those learners who need it the most do not seek help (appropriately). In this exploratory study, we investigated re-reading as a unique window into elementary help-seeking processes. Students had to learn the content of multiple hypertext pages of different complexity for a subsequent knowledge test. After this learning phase we randomly assigned learners to two experimental groups: The memory control group (MG, n = 14) directly answered the knowledge test and the experimental help-seeking group (HSG, n = 15) had the option to re-read the hypertext pages before answering. Results show that HSG students outperformed MG students and that HSG students strongly adapted the extent and frequency of their re-reading to task complexity and the complexity of the hypertext pages. However, more re-reading or more adaptivity did not automatically enhance performance on the knowledge test. The implications of these findings for the design of adaptive (metacognitive) help functions in computer-based learning environments will be discussed.

Meta-cognitive skills to be developed in learning for the 21st century is the detection and correction of errors in solutions. These meta-cognitive skills can help to detect errors the learner has made her/himself as well as errors others have made. Our investigations in learning from errors have the ultimate goal to adapt the selection and presentation to the learner so that he/she can better learn from erroneous examples others have made. In our experiments we found that (1) erroneous examples with help provision can promote students skill of find errors, (2) the benefit from erroneous examples depends on the relation between the student's level and the example's difficulty, i.e. if the student is prepared for the problem, (3) for many students it is very difficult to correct errors.

Learners that have better metacognition acquire knowledge faster than others who do not. If we had better models of such learning, we would be able to build a better metacognitive educational system. In this paper, we propose a computational model that uses a probabilistic context free grammar induction algorithm yielding metacognitive learning by acquiring deep features to assist future learning. We discuss the challenges of integrating this model into a synthetic student, and possible future studies in using this model to better understand human learning. Preliminary results suggest that both stronger prior knowledge and a better learning strategy can speed up the learning process. Some model variations generate human-like error pattern.

Developing the capabilities of children to comprehend written texts is key to their development as young adults. Text comprehension skills develop enormously from the age of 7- 8 until the age of 11. Nowadays, several young children (˜5% – 10% of novice readers) turn out to be poor (text) comprehenders: they demonstrate text comprehension difficulties, related to inference-making skills, despite proficiency in lowlevel cognitive skills like word decoding. Though there are several pencil-and-paper reading interventions for improving inference-making skills on text, and addressed to poor comprehenders, the design and evaluation of Adaptive Learning Systems (ALSs) are lagging behind. The use of more intelligent ALSs to custom-tailor such interventions in the form of games for poor comprehenders has tremendous potential. Our system embodies that potential. This paper presents the design of our ALS by focusing on its intelligent adaptive engine and the related conceptual models, and by presenting the visual interfaces for story telling and gaming.