Showing papers on "Commonsense reasoning published in 2012"

Sentic activation: a two-level affective common sense reasoning framework

Abstract: An important difference between traditional AI systems and human intelligence is our ability to harness common sense knowledge gleaned from a lifetime of learning and experiences to inform our decision making and behavior. This allows humans to adapt easily to novel situations where AI fails catastrophically for lack of situation-specific rules and generalization capabilities. Common sense knowledge also provides the background knowledge for humans to successfully operate in social situations where such knowledge is typically assumed. In order for machines to exploit common sense knowledge in reasoning as humans do, moreover, we need to endow them with human-like reasoning strategies. In this work, we propose a two-level affective reasoning framework that concurrently employs multi-dimensionality reduction and graph mining techniques to mimic the integration of conscious and unconscious reasoning, and exploit it for sentiment analysis.

Some Assembly Required: How Scientific Explanations Are Constructed during Clinical Interviews.

Abstract: This article is concerned with commonsense science knowledge, the informally gained knowledge of the natural world that students possess prior to formal instruction in a scientific discipline. Although commonsense science has been the focus of substantial study for more than two decades, there are still profound disagreements about its nature and origin, and its role in science learning. What is the reason that it has been so difficult to reach consensus? We believe that the problems run deep; there are difficulties both with how the field has framed questions and the way that it has gone about seeking answers. In order to make progress, we believe it will be helpful to focus on one type of research instrument—the clinical interview—that is employed in the study of commonsense science. More specifically, we argue that we should seek to understand and model, on a moment-by-moment basis, student reasoning as it occurs in the interviews employed to study commonsense science. To illustrate and support this claim, we draw on a corpus of interviews with middle school students in which the students were asked questions pertaining to the seasons and climate phenomena. Our analysis of this corpus is based on what we call the mode-node framework. In this framework, student reasoning is seen as drawing on a set of knowledge elements we call nodes, and this set produces temporary explanatory structures we call dynamic mental constructs. Furthermore, the analysis of our corpus seeks to highlight certain patterns of student reasoning that occur during interviews, patterns in what we call conceptual dynamics. These include patterns in which students can be seen to search through available knowledge (nodes), in which they assemble nodes into an explanation, and in which they converge on and shift among alternative explanations. 2011 Wiley

Cooperative knowledge based perceptual anchoring

Abstract: In settings where heterogenous robotic systems interact with humans, information from the environment must be systematically captured, organized and maintained in time. In this work, we propose a model for connecting perceptual information to semantic information in a multi-agent setting. In particular, we present semantic cooperative perceptual anchoring, that captures collectively acquired perceptual information and connects it to semantically expressed commonsense knowledge. We describe how we implemented the proposed model in a smart environment, using different modern perceptual and knowledge representation techniques. We present the results of the system and investigate different scenarios in which we use the commonsense together with perceptual knowledge, for communication, reasoning and exchange of information.

A model for “crisp reasoning” with fuzzy sets

Abstract: In the setting of a general type of fuzzy algebras, this paper deals with a new theoretic view on the commonsense reasoning, consisting of a kind of Popper's search for conjectures and refutations. It is supposed that the reasoning is done in natural language, but only with nonambiguous precise and imprecise terms, respectively, represented by crisp and fuzzy sets. © 2012 Wiley Periodicals, Inc. © 2012 Wiley Periodicals, Inc.

Modelling time and reliability in structured argumentation frameworks

Abstract: Argumentation is a human-like reasoning mechanism contributing to the formalization of commonsense reasoning. In the last decade, several argument-based formalisms have emerged, with application in many areas, such as legal reasoning, autonomous agents and multi-agent systems; many are based on Dung's seminal work characterizing Abstract Argumentation Frameworks (AF). Recent research in the area has led to Temporal Argumentation Frameworks (TAF) that extend Dung's by considering the temporal availability of arguments. In this work we introduce a novel framework, called Extended Temporal Argumentation Framework (E-TAF), extending TAF with the capability of modeling availability of attacks among arguments, which allows for instance to model reliability of arguments varying over time. We show how E-TAF can be enriched by considering Structured Abstract Argumentation, adding compositional elements to the abstract arguments involved based on a simplified version of the recently introduced Dynamic Argumentation Frameworks.

Diagnostic Test Approaches to Machine Learning and Commonsense Reasoning Systems

Abstract: Recommender systems are becoming an inseparable part of many modern Internet web sites and web shops. The quality of recommendations made may significantly influence the browsing experience of the user and revenues made by web site owners. Developers can choose between a variety of recommender algorithms; unfortunately no general scheme exists for evaluation of their recall and precision. In this chapter, the authors propose a method based on cross-validation for diagnosing the strengths and weaknesses of recommender algorithms. The method not only splits initial data into a training and test subsets, but also splits the attribute set into a hidden and visible part. Experiments were performed on a userbased and item-based recommender algorithm. These algorithms were applied to the MovieLens dataset, and the authors found classical user-based methods perform better in terms of recall and precision.

Bridging vision and commonsense for multimodal situation recognition in pervasive systems

Abstract: Pervasive services may have to rely on multimodal classification to implement situation-recognition. However, the effectiveness of current multimodal classifiers is often not satisfactory. In this paper, we describe a novel approach to multimodal classification based on integrating a vision sensor with a commonsense knowledge base. Specifically, our approach is based on extracting the individual objects perceived by a camera and classifying them individually with non-parametric algorithms; then, using a commonsense knowledge base, classifying the overall scene with high effectiveness. Such classification results can then be fused together with other sensors, again on a commonsense basis, for both improving classification accuracy and dealing with missing labels. Experimental results are presented to assess, under different configurations, the effectiveness of our vision sensor and its integration with other kinds of sensors, proving that the approach is effective and able to correctly recognize a number of situations in open-ended environments.

Web@IDSS - Argumentation-enabled Web-based IDSS for reasoning over incomplete and conflicting information

Abstract: Over the past few decades, there has been a resurgence of interest in using high-level software intelligence for business intelligence (BI). The objective is to produce actionable information that is delivered at the right time, easily comprehendible and exportable to other software to assist business decision-making processes. Although the design and development of decision support systems (DSS) has been carried out for over 40 years, DSS still suffer from many limitations such as poor maintainability, poor flexibility and less reusability. The development of the Internet and WWW has helped information systems to overcome those limitations and Web DSS is now an active area of research in business intelligence, impacting significantly on the way information is exchanged and businesses are conducted. However, to remain competitive, companies rely on business intelligence (BI) to continually monitor and analyze the operating environment (both internal and external), to identify potential risks, and to devise competitive business strategies. However, the current Web DSS applications are not able to reason over information present across organizational boundaries which could be incomplete and conflicting. The use of an argumentation-based mechanism has not been explored to address such shortcomings in Web DSS. Argumentation is a kind of commonsense reasoning used by human beings to reach a justifiable conclusion when available information is incomplete and/or inconsistent among participants. In this paper, we propose and elaborate in detail a conceptual framework and formal argumentation-based semantics for Web enabled Intelligent DSS (Web@IDSS). We evaluate the use of argumentative reasoning in Web DSS with the help of a case study, prototype development and future directions. Applications built according to the proposed framework will provide more practical, understandable results to decision makers.

Discussion paper: how much of commonsense and legal reasoning is formalizable? A review of conceptual obstacles

Abstract: Fifty years of effort in artificial intelligence (AI) and the formalization of legal reasoning have produced both successes and failures. Considerable success in organizing and displaying evidence and its interrelationships has been accompanied by failure to achieve the original ambition of AI as applied to law: fully automated legal decision-making. The obstacles to formalizing legal reasoning have proved to be the same ones that make the formalization of commonsense reasoning so difficult, and are most evident where legal reasoning has to meld with the vast web of ordinary human knowledge of the world. Underlying many of the problems is the mismatch between the discreteness of symbol manipulation and the continuous nature of imprecise natural language, of degrees of similarity and analogy, and of probabilities.

An approach to evaluate AI commonsense reasoning systems

Abstract: We propose and give a preliminary test of a new metric for the quality of the commonsense knowledge and reasoning of large AI databases: Using the same measurement as is used for a four-year-old, namely, an IQ test for young children. We report on results obtained using test questions we wrote in the spirit of the questions of the Wechsler Preschool and Primary Scale of Intelligence, Third Edition (WPPSI-III) on the ConceptNet system, which were, on the whole, quite strong.

The robot baby and massive metacognition: Future vision

Abstract: Metacognition is a powerful tool that can play machine learning and commonsense reasoning off one another synergistically Based on our previous work in metacognition, we present the vision of a long-term project called “Robot in a Room” in this paper Similar to newborn babies trying to learn about themselves, surroundings and things that they are able to do, this new project involves a mobile robot that does not know about its environment and its own capabilities ie it does not start with a robust self-model However, it has a primary goal: to learn about itself and explore its environment (the room it lives in)

Using Textual Patterns to Learn Expected Event Frequencies

Abstract: Commonsense reasoning requires knowledge about the frequency with which ordinary events and activities occur: How often do people eat a sandwich, go to sleep, write a book, or get married? This paper introduces work to acquire a knowledge base pairing factoids about such events with frequency categories learned from simple textual patterns. We are releasing a collection of the resulting event frequencies, which are evaluated for accuracy, and we demonstrate an initial application of the results to the problem of knowledge refinement.

Trichotomies in the Complexity of Minimal Inference

Abstract: We study the complexity of the propositional minimal inference problem. Although the complexity of this problem has been already extensively studied before because of its fundamental importance in nonmonotonic logics and commonsense reasoning, no complete classification of its complexity was found. We classify the complexity of four different and well-studied formalizations of the problem in the version with unbounded queries, proving that the complexity of the minimal inference problem for each of them has a trichotomy (between P, coNP-complete, and Π2P-complete). One of these results finally settles with a positive answer the trichotomy conjecture of Kirousis and Kolaitis (Theory Comput. Syst. 37(6):659–715, 2004). In the process we also strengthen and give a much simplified proof of the main result from Durand and Hermann (Proceedings 20th Symposium on Theoretical Aspects of Computer Science (STACS 2003), pp. 451–462, 2003).

Commonsense Knowledge for the Collection of Ground Truth Data on Semantic Descriptors

Abstract: The coverage of the semantic gap in video indexing and retrieval has gone through a continuous increase of the vocabulary of high -- level features or semantic descriptors, sometimes organized in light -- scale, corpus -- specific, computational ontologies. This paper presents a computer -- supported manual annotation method that relies on a very large scale, shared, commonsense ontologies for the selection of semantic descriptors. The ontological terms are accessed through a linguistic interface that relies on multi -- lingual dictionaries and action/event template structures (or frames). The manual generation or check of annotations provides ground truth data for evaluation purposes and training data for knowledge acquisition. The novelty of the approach relies on the use of widely shared large -- scale ontologies, that prevent arbitrariness of annotation and favor interoperability. We test the viability of the approach by carrying out some user studies on the annotation of narrative videos.

Common-Sense knowledge for a computer vision system for human action recognition

Abstract: This work presents a novel approach for human action recognition based on the combination of computer vision techniques and common-sense knowledge and reasoning capabilities. The emphasis of this work is on how common sense has to be leveraged to a vision-based human action recognition so that nonsensical errors can be amended at the understanding stage. The proposed framework is to be deployed in a realistic environment in which humans behave rationally, that is, motivated by an aim or a reason.

Consciousness and Commonsense Critics in Cognitive Architectures: Case Study of Society of Mind Cognitive Architecture

Abstract: The research identifies the concepts of consciousness and commonsense. It also investigates and demonstrates how consciousness level of an agent and its common sense reasoning abilities can improve the performance and intelligence using SMCA Society of Mind Cognitive Architecture as a case study. Consciousness is a sense of awareness about oneself and the surroundings in which the animal or human being lives. This gives a connection between a non materialistic mind and a materialistic brain. Common sense in common world is one that is immediately perceived by everyone from a given environment. A six tiered layers SMCA control model is designed that relies on a society of agents operating using metrics associated with the principles of artificial economics in animal cognition. SMCA is a society or collection of agents, where agents tasks implemented on testbed, demonstrates simple to complex level of consciousness and commonsense.

Commonsense psychology, dual visual streams, and the individuation of action

Abstract: Psychologists and philosophers are often tempted to make general claims about the importance of certain experimental results for our commonsense notions of intentional agency, moral responsibility, and free will. It is a strong intuition that if the agent does not intentionally control her own behavior, her behavior will not be an expression of agency, she will not be morally responsible for its consequences, and she will not be acting as a free agent. It therefore seems natural that the interest centers on the notion of intentional control. If it can be experimentally shown that agents do as a matter of fact not control their own actions, even though they think they do, it will have far reaching consequences for our moral psychology. In this paper I look at recent eliminative arguments allegedly demonstrating that our commonsense notion of intentional control is incompatible with experimental data in support of the dual visual stream theory.

The robot baby and massive metacognition: Early steps via growing neural gas

Abstract: We have initiated a long-term robotics project based on our previous work on metacognition as a powerful tool that can synergistically play machine learning and commonsense reasoning off one another The new project involves a mobile robot that lives in a room and learns about the room and about itself The robot is initially set up to have a standard set of facilities (vision, IR, limb, wheels, planners, learning modules, some modest NLP, a reasoner, etc) but it does not know much about its capabilities or how to properly use them It has a prime directive: to learn This paper will focus on one of the first major questions of this project: can we use Growing Neural Gas (GNG) to discover the physical structure of an environment and, if so, what are the limits of its use? To answer this question, we have devised an experiment to test whether our robot can distinguish between two identical objects using only GNG Preliminary results suggest that passing image data along with robotic control signal data is sufficient to autonomously detect the basic physical structure of a room

Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence

Abstract: The problem of replicating the flexibility of human common-sense reasoning has captured the imagination of computer scientists since the early days of Alan Turing’s foundational work on computation and the philosophy of artificial intelligence. In the intervening years, the idea of cognition as computation has emerged as a fundamental tenet of Artificial Intelligence (AI) and cognitive science. But what kind of computation is cognition? We describe a computational formalism centered around a probabilistic Turing machine called QUERY, which captures the operation of probabilistic conditioning via conditional simulation. Through several examples and analyses, we demonstrate how the QUERY abstraction can be used to cast common-sense reasoning as probabilistic inference in a statistical model of our observations and the uncertain structure of the world that generated that experience. This formulation is a recent synthesis of several research programs in AI and cognitive science, but it also represents a surprising convergence of several of Turing’s pioneering insights in AI, the foundations of computation,

Consistent Query Answering Using Relational Databases through Argumentation

Abstract: This paper introduces a framework that integrates a reasoner based on defeasible argumentation with a large information repository backed by one or several relational databases In our scenario, we assume that the databases involved are updated by external independent applications, possibly introducing inconsistencies in a particular database, or leading to inconsistency among the subset of databases that refer to the same data Argumentation reasoning will contribute with the possibility of obtaining consistent answers from the information repository with the properties described We present the Database Integration for Defeasible Logic Programming (DBI-DeLP) framework, which enables commonsense reasoning based on Defeasible Logic Programming (DeLP) by extending the system capabilities to handle large amounts of data and providing consistent answers for queries posed to it

Affect Detection from Social Contexts Using Commonsense Knowledge Representations

Abstract: In the past years, an important volume of research in Natural Language Processing has concentrated on the development of automatic systems to deal with affect in text. In spite of this interest, the performance of the approaches is still very low. An explanation to this fact is that emotion is most of the times not expressed through specific words, but by evoking situations that have an affective meaning. Dealing with this phenomenon requires automatic systems to have "knowledge"on the situation, the concepts it describes and their interaction. This necessity motivated us to develop the EmotiNet knowledgebase -- a resource for the detection of emotion from text based on commonsense knowledge on concepts, their interaction and their affective consequence. In this article, we present an overview of the process undergone to build EmotiNet, propose methods to extend the knowledge it contains and analyze the performance of implicit affect detection using this resource. Additionally, we compare the results obtained with EmotiNet to the use of well-established methods for affect detection. The results of our extensive evaluations show that the approach using EmotiNet is appropriate for capturing and storing the structure of implicitly expressed affect, that the knowledge it contains can be easily extended to improve the results of this task and that methods employing EmotiNet obtain better results than existing methods for emotion detection.

Experiences on sensor fusion with commonsense reasoning

Abstract: Multi-modal sensor fusion recently became a widespread technique to provide pervasive services with context-recognition capabilities. However, classifiers commonly used to implement this technique are still far from being perfect. Thus, fusion algorithms able to deal with significant inaccuracies are required. In this paper we present preliminary results obtained with a novel approach that combines diverse classifiers through commonsense reasoning. The approach maps classification labels produced by classifiers to concepts organized within the ConceptNet network. Then it verifies their semantic proximity by implementing a greedy sub-graph search algorithm. Specifically, different classifiers are fused together on a commonsense basis for both: (i) improving classification accuracy and (ii) dealing with missing labels. Experimental results are discussed through a real-world case study in which three classifiers are fused to recognize both user activities and locations.

How much of commonsense and legal reasoning is formalizable? A review of conceptual obstacles

Abstract: Fifty years of effort in artificial intelligence (AI) and the formalization of legal reasoning have produced both successes and failures. Considerable success in organizing and displaying evidence and its interrelationships has been accompanied by failure to achieve the original ambition of AI as applied to law: fully automated legal decision-making. The obstacles to formalizing legal reasoning have proved to be the same ones that make the formalization of commonsense reasoning so difficult, and are most evident where legal reasoning has to meld with the vast web of ordinary human knowledge of the world. Underlying many of the problems is the mismatch between the discreteness of symbol manipulation and the continuous nature of imprecise natural language, of degrees of similarity and analogy, and of probabilities.

Reasoning with disposition using DNA tweezers

Abstract: In this paper, we consider dynamic DNA devices called DNA tweezers whose operation is based on the mechanism of DNA strand displacement. We show how the systematic use of this simple but robust mechanism makes it possible to produce a DNA-fuelled molecular machine for reasoning with dispositions which are essential ingredients of commonsense of an individual. A biochemical reaction on DNA strands is used to activate DNA tweezers for reasoning with dispositions taken from the commonsense-based knowledge base. The dispositions are basically propositions that are preponderantly but not necessarily always true. The concept of dispositionality is closely related to the notion of usuality which provides a computational framework for commonsense reasoning. As human perception is usually represented in a vague qualitative fashion, we consider fuzzy set as one tool of engineering and try to mimic human intelligence of reasoning based on perception. Since childhood, an individual perceives the world around him/her and accordingly makes several commonsense-based judgements which are essentially reasoning with dispositions.

Hardware Implementation of Fuzzy Default Logic

Abstract: The chapter presents hardware implementation of the model of commonsense reasoning system based on a new formalism Fuzzy Default Logic (FDL). It briefly recalls main definitions and algorithms of FDL technique in a form of software oriented procedures. Basic building blocks used for implementation are presented. Then the software algorithms of the FDL model are transformed into hardware blocks. The entire hardware structure has been implemented in FPGA Xilinx Virtex5 device. The obtained results, examples of experiments and applications in system verification platform are discussed and further research tasks formulated.

Commonsense knowledge acquisition through children's stories

Abstract: Humans interact with each other using their collection of commonsense knowledge about everyday concepts and their relationships. To establish a similar natural form of interaction with computers, they should be given the same collection of knowledge. Various research works have focused on building large-scale commonsense knowledge that computers can use. But capturing and representing commonsense knowledge into a machine-usable repository, whether manual or automated, are still far from completion. This research explores an approach to acquiring commonsense knowledge through the use of children's stories. Relation extraction templates are also utilized to store the learned knowledge into an ontology, which can then be used by automatic story generators and other applications with children as the target users.

Intelligent decision-making approach based on fuzzy-causal knowledge and reasoning

Abstract: Our intelligent decision-making approach (IDMA) is an instance of cognitive computing. It applies causality as common sense reasoning and fuzzy logic as a representation for qualitative knowledge. Our IDMA collects raw knowledge of humans through psychological models to tailor a knowledge-base (KB). The KB manages different repositories (e.g., cognitive maps (CM) and an ontology) to depict the object of study. The IDMA traces fuzzy-causal inferences to simulate causal behavior and estimate causal outcomes for decision-making. In order to test our approach, it is linked to the sequencing module of an intelligent and adaptive web-based educational system (IAWBES). It is used to provide student-centered education and enhance the students' learning by intelligent and adaptive functionalities. The results reveal users of an experimental group reached 17% of better learning than their peers of the control group.

An Automatic Decomposition Method for Qualitative Spatial and Temporal Reasoning

Abstract: Qualitative spatial and temporal reasoning is a research field that studies relational, constraint-based formalisms for representing, and reasoning about, spatial and temporal information. The standard approach for checking consistency is based on an exhaustive representation of possible configurations between three entities, the so-called composition tables. These tables, however, encode semantic background knowledge in a redundant way, which becomes a size and efficiency issue, when the composition table needs to be grounded as done in SAT encodings of problem instances. % In this paper, we present a new framework that allows for decomposing composition tables into logically simpler parts, while preserving logical equivalence, e.g., the decomposition in start- and end-points for Allen's Interval Calculus. We show that finding such decompositions is an NP-complete problem and present a SAT-based method to generate decompositions. Finally, we discuss the impact of our decomposition method on SAT encodings of problem instances, and present a reasoning system built on decompositions that compares favorably with state-of-the-art solvers.

Ambiguous command understanding with commonsense

Abstract: This paper proposes our approach to disambiguate human pointing gesture by using commonsense knowledge. Pointing gesture is a natural way to specify the object that a user needs in the “Bring something” service. However, error in gesture recognition makes robot difficult to select the correct candidate object when there are multiple objects located closely together. To solve this problem, Robot Technology (RT) Ontology was used to make assumption about human activity and necessary objects for the activity. By combining this commonsense reasoning with the spatial constrain from human's pointing direction, robot is able to find appropriate object. Experiment showed the successful rate of object selection was improved, and therefore robotic service becomes more intuitive.