Papers by Bipin Indurkhya
We have developed an answer verification system for helping visually impaired people who are lear... more We have developed an answer verification system for helping visually impaired people who are learning how to use a spreadsheet software by answering problem-solving exercises. Visually impaired learners have difficulty in verifying their answers on their own with conventional software tools. Hence, the answer verification system is designed to provide feedback to the learners with respect to the numbers of errors in their answers, the error locations, and the reasons behind the errors. The messages output from our system can be read out by a screen reader, and our system can treat various kinds of problem-solving exercises of a spreadsheet software. We conducted an evaluation study of our system both with the teachers and the students to assess its usability and functionality. Based on the results of this study, we generated an improved version of our system, which is also described here.
European Journal of Combinatorics, 2003
We describe here our ongoing research on modeling conceptual and narrative structure of fairytale... more We describe here our ongoing research on modeling conceptual and narrative structure of fairytales by a computer system. In this paper we focus on the variations of fairytales based on Cinderella from all around the world. We analyzed twenty-three Japanese texts of Cinderella tales and modeled their conceptual and narrative structures using the notions of composition elements and motifs. We then incorporated all these structures into a unified structural model of Cinderella story. Finally, we implemented a computer system based on the unified structural model to automatically generate variations of Cinderella tales. The system was able to generate variations that were quite different from any of the original Cinderella tales.
Proceedings of the Annual Meeting of the Cognitive Science Society, 2009
The paper describes various reading experiments to investigate human reading patterns for Hindi a... more The paper describes various reading experiments to investigate human reading patterns for Hindi and Telugu. Experiments are based on different types of word jumbling. Results from these experiments bring out some interesting observations which are related to orthography, morphology, syntax, semantics, and discourse. These patterns were noticed across majority of the subjects. Some of these observations are unique to Hindi and Telugu.
The journal of problem solving, Jul 22, 2015
is the task to fast analyze a large amount of multimedia data like images or videos and accuratel... more is the task to fast analyze a large amount of multimedia data like images or videos and accurately find the ones relevant to a certain semantic meaning. Although LSMR has been investigated for more than two decades in the fields of multimedia processing and computer vision, a more interdisciplinary approach is necessary to develop an LSMR system that is really meaningful for humans. To this end, this paper aims to stimulate attention to the LSMR problem from diverse research fields. By explaining basic terminologies in LSMR, we first survey several representative methods in chronological order. This reveals that due to prioritizing the generality and scalability for large-scale data, recent methods interpret semantic meanings with a completely different mechanism from humans, though such humanlike mechanisms were used in classical heuristic-based methods. Based on this, we discuss human-machine cooperation, which incorporates knowledge about human interpretation into LSMR without sacrificing the generality and scalability. In particular, we present three approaches to human-machine cooperation (cognitive, ontological, and adaptive), which are attributed to cognitive science, ontology engineering, and metacognition, respectively. We hope that this paper will create a bridge to enable researchers in different fields to communicate about the LSMR problem and lead to a ground-breaking next generation of LSMR systems.
arXiv (Cornell University), Mar 7, 2018
International Journal on Document Analysis and Recognition, Jan 17, 2019
arXiv (Cornell University), Jan 20, 2019
International Conference on Computers in Education, 2002. Proceedings.
ICT Innovations 2016, 2017
Affective computing is concerned with designing and implementing emotionally intelligent machines... more Affective computing is concerned with designing and implementing emotionally intelligent machines. Three major subareas of research in this field are: (1) sensing the emotional state of the user, (2) expressing or displaying emotional states in a robot or an avatar, and (3) manipulating the users emotional state. For example, Picard [1] has designed a system to infer emotional state of the user based on their facial expressions.
empts to answer this question. The paradox of interactionism, in his view, arises from maintainin... more empts to answer this question. The paradox of interactionism, in his view, arises from maintaining both that the attributes and structures a cognitive agent uses to conceptualize its environment can be created differently, and that this creation is not arbitrary but somehow constrained by an environment that does not have a pre-existing structure. Indurkhya concludes that neither the philosophical tradition from Kant to Goodman, Piaget's constructivism, nor Lakoff and Johnson's experiential view adequately resolves this paradox. These first four chapters constitute part ! of the book, "The Problem." In Part II, "A Theory," Indurkhya reveals his interactionist approach to cognition (Chapter 5), gives a formal characterization of this theory (Chapter 6), and develops his theory of metaphor (Chapter 7). I will discuss these chapters more fully below. Part III of the book, "The Implications," applies his theoretical framework to other concerns surro...
Lecture Notes in Computer Science, 2014
Highlights A novel method for text-independent writer identification. Organization of trainin... more Highlights A novel method for text-independent writer identification. Organization of training samples for Convolutional Neural Network. Feature aggregation to form global features from local features. 99.97% accuracy to classify 100 writers by 200 characters for handwritten Japanese.
New Ideas in Psychology, 2007
... Thus, the problem is to somehow allow creative changes of ontology, but to rule out arbitrary... more ... Thus, the problem is to somehow allow creative changes of ontology, but to rule out arbitrary changes of ontology; or, at least, to constrain which inferences are rationally acceptable from the changed ontology. (Palmer, 1992, pp. ...
Studies in Cognitive Systems, 1992
In my framework of cognition, the paradox of interactionism is resolved by pointing out that whil... more In my framework of cognition, the paradox of interactionism is resolved by pointing out that while it is the cognitive agent who gives an ontology to the external world by instantiating concept networks, the structure of the world, as seen from this ontology, is determined by reality. Thus, it is only by instantiating different concept networks that the cognitive agent can ‘see’ different structures in reality. In other words, any reorganization and restructuring of the world view is essentially the process of reinstantiating the concept networks—a process I have been calling projection.
We propose here a new approach to legal thinking that is based on principles of Gestalt perceptio... more We propose here a new approach to legal thinking that is based on principles of Gestalt perception. Using a Gestalt view of perception, which sees perception as the process of building a conceptual representation of the given stimulus, we articulate legal thinking as the process of building a representation for the given facts of a case. We propose a model in which top-down and bottom-up processes interact together to build arguments (or representations) in legal thinking. We discuss some implications of our approach, especially with respect to modeling precedential reasoning and creativity in legal thinking.
2010 IEEE International Conference on Robotics and Biomimetics, 2010
Studies in Cognitive Systems, 1992
Proceedings of the 22nd ACM conference on Hypertext and hypermedia - HT '11, 2011
Google, Inc. (search). ... An algorithm to generate engaging narratives through non-linearity. Fu... more Google, Inc. (search). ... An algorithm to generate engaging narratives through non-linearity. Full Text: PDF PDF. ... Cornell University Press, 1980. 6. YG Cheong. A computational model of narrativegeneration for suspense. In AAAI. AAAI Press, 2006. 7. V. Chilukuri and B. Indurkhya. ...
Minds and Machines - MIND MACH, 2000
New Ideas in Psychology, 2006
... A computational theory of metaphor comprehension and analogical reasoning (semantics, predica... more ... A computational theory of metaphor comprehension and analogical reasoning (semantics, predicate-calculus, cognitive, artificial intelligence, natural language processing). Author: BipinIndurkhya, Publication: ... An abstract is not available. top of page AUTHORS. Bipin Indurkhya ...
Uploads
Papers by Bipin Indurkhya