Refine
Year of publication
Document Type
Way of publication
- Open Access (2)
Keywords
- machine learning (2)
- Biosemiotik (1)
- Cognitive system (1)
- Cognitive systems (1)
- Computational cognition (1)
- Computational linguistics (1)
- Fock space (1)
- Künstliche Intelligenz (1)
- Maschinensemiotik (1)
- Matlab (1)
- Petri net transducer and behaviour control (1)
- Petrinetze (1)
- Quantum logic (1)
- Reinforcement Learning (1)
- Semantics processing (1)
- Semiotics (1)
- attention modeling (1)
- cognitive agents (1)
- cognitive systems (1)
- dynamic semantics (1)
- feature-valuesrelation (1)
- fossilization (1)
- image schema theory (1)
- inner stage (1)
- intuitive interaction (1)
- ontology inference (1)
- pragmatic implicatures (1)
- quantum field theory (1)
- veridicality (1)
Institute
Semantic Dialogue Modeling
(2012)
Little Drop of Mulligatawny Soup, Miss Sophie? Automatic Speech Understanding provided by Petri Nets
(2017)
We report on research conducted as part of the Universal Cognitive User Interface (UCUI) project, which aims at developing a universal, autarkic module for intuitive interaction with technical devices. First, we present an empirical study of image schemas as basic building blocks of human knowledge. Image schemas have been studied extensively in cognitive linguistics, but insufficiently in the context of human-computer-interaction (HCI). Some image
schemas are developed early at pre-verbal stages (e.g., up-down) and may, thus, exert greater influence on human knowledge than later developed image schemas (e.g., centre-periphery). To investigate this for HCI contexts, we applied a speech interaction task using a Wizard of Oz paradigm. Our results show that users apply early image schemas more frequently than late image schemas. They should, therefore, be given preference in interface designs. In the second
part of this contribution we therefore focus on the appropriate representation and processing of semantics. We introduce novel theoretical work including feature-values-relations and Petri net
transducers, and discuss their impact on behaviour control of cognitive systems. In addition, we illustrate some details of the implementation regarding learning strategies and the graphical
user interface.
Vector symbolic architectures (VSA) are a viable approach for the hyperdimensional representation of symbolic data, such as documents, syntactic structures, or semantic frames. We present a rigorous mathematical framework for the representation of phrase structure trees and parse trees of context-free grammars (CFG) in Fock space, i.e. infinite-dimensional Hilbert space as being used in quantum field theory. We define a novel normal form for CFG by means of term algebras. Using a recently developed software toolbox, called FockBox, we construct Fock space representations for the trees built up by a CFG left-corner (LC) parser. We prove a universal representation theorem for CFG term algebras in Fock space and illustrate our findings through a low-dimensional principal component projection of the LC parser state. Our approach could leverage the development of VSA for explainable artificial intelligence (XAI) by means of hyperdimensional deep neural computation.
Cognitive agents that act independently and solve problems in their environment on behalf of a user are referred to as autonomous. In order to increase the degree of autonomy, advanced cognitive architectures also contain higher-level psychological modules with which needs and motives of the agent are also taken into account and with which the behavior of the agent can be controlled. Regardless of the level of autonomy, successful behavior is based on interacting with the environment and being able to communicate with other agents or users. The agent can use these skills to learn a truthful knowledge model of the environment and thus predict the consequences of its own actions. For this purpose, the symbolic information received during the interaction and communication must be converted into representational data structures so that they can be stored in the knowledge model, processed logically and retrieved from there. Here, we firstly outline a grammar-based transformation mechanism that unifies the description of physical interaction and linguistic communication and on which the language acquisition is based. Specifically, we use minimalist grammar (MG) for this aim, which is a recent computational implementation of generative linguistics. In order to develop proper cognitive information and communication technologies, we are using utterance meaning transducers (UMT) that are based on semantic parsers and a mental lexicon, comprising syntactic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. To this aim we outline a reinforcement learning algorithm for the acquisition of syntax and semantics of English utterances. English declarative sentences are presented to the agent by a teacher in form of utterance meaning pairs (UMP) where the meanings are encoded as formulas of predicate logic. Since MG codifies universal linguistic competence through inference rules, thereby separating innate linguistic knowledge from the contingently acquired lexicon, our approach unifies generative grammar and reinforcement learning, hence potentially resolving the still pending Chomsky-Skinner controversy.
btuktuminglear, btuktsptech, btuktcogsys
Machine Semiotics
(2023)
Recognizing a basic difference between the semiotics of humans and machines presents a possibility to overcome the shortcomings of current speech assistive devices. For the machine, the meaning of a (human) utterance is defined by its own scope of actions. Machines, thus, do not need to understand the conventional meaning of an utterance. Rather, they draw conversational implicatures in the sense of (neo-)Gricean pragmatics. For speech assistive devices, the learning of machine-specific meanings of human utterances, i.e. the fossilization of conversational implicatures into conventionalized ones by trial and error through lexicalization appears to be sufficient. Using the quite trivial example of a cognitive heating | device, we show that — based on dynamic semantics — this process can be formalized as the reinforcement learning of utterance-meaning pairs (UMP).
We present a model, inspired by quantum field theory, of the so-called inner stage of technical cognitive agents. The inner stage represents all knowledge of the agent. It allows for planning of actions and for higher cognitive functions like coping and fantasy. By the example of a cognitive mouse agent living in a maze wold, we discuss learning, action planning, and attention in a fully deterministic setting and assuming a totally observable world. We explain the relevance of our approach to cognitive infocommunications.
In this contribution, we want to summarize recent development steps of theembeddedcognitive user interfaceUCUI, which enables auser-adaptive scenario inhuman-machine or even human-robot interactions by considering sophisticated cognitive andsemantic modelling.The interface prototype is developed by differentGerman institutes and companies with their steering teams at Fraunhofer IKTS and Brandenburg University of Technology. The interface prototype is able to communicate with users viaspeech andgesture recognition, speech synthesis and a touch display. The device includes an autarkic semantic processing and beyond a cognitive behavior control, which supportsan intuitive interaction to controldifferent kindsof electronic devices,e.g. in a smart home environment or in interactive respectively collaborative robotics.Contraryto available speech assistance systems such as Amazon Echo or Google Home, the introduced cognitive user interface UCUIensuresthe user privacy by processing all necessary informationwithout any network access ofthe interface device.
We present a Matlab toolbox, called “FockBox”, handling
Fock spaces and objects associated with Fock spaces: scalars, ket and
bra vectors, and linear operators. We give brief application examples
from computational linguistics, semantics processing, and quantum logic,demonstrating the use of the toolbox.
Das Fachgebiet der Kognitiven Technischen Systeme zeichnet sich durch einen hohen Grad an Interdisziplinarität (z. B. Kenntnisse auf den Gebieten Biologie, Psychologie, Informatik und den Ingenieurwissenschaften) aus. Nach wie vor besteht Bedarf an einer methodischen Darstellung des Fachgebietes, bei der die theoretische Durchdringung von Zusammenhängen zwischen den verschiedenen Wissensgebieten zusätzlich durch Anschaulichkeit unterstützt wird. Die vorliegende Arbeit stellt einen Fortschrittsbericht zur Realisierung eines Forschungs- und Experimentiersystems dar, mit dem wir dieses Anliegen unterstützen und über das wir erstmals konzeptionell in [1] berichtet haben. In diesem Beitrag folgen wir einem integrativen Ansatz zur Entwicklung einer kognitiven Architektur, mit der unter Verwendung repräsentationaler Datenstrukturen adaptives Verhalten auf verschiedenen Zeitskalen sowie zwei wichtige Verhaltensprogramme für das Problemlösen (Objektfindung, Exploration) auf der gemeinsamen Grundlage von Markov-Entscheidungsprozessen umgesetzt werden. Mit einem Kurzbericht zum Entwicklungsstand der physikalischen Experimentierumgebung und einer Zusammenfassung der bislang erreichten Ergebnisse beschließen wir den diesjährigen Beitrag.
In diesem Text wird das in „Maschinensemiotik“ [12] vorgestellte Verfahren zur Verknüpfung von Äußerungen mit deren Bedeutung weiterentwickelt und in Form von Algebraischen Petri-Netzen [20] modelliert. Gleichzeitig wird der Formalismus der Petri-Netze nebenbei eingeführt, wobei die Vorstellung nicht auf formale Vollständigkeit abzielt, sondern nur das für die Anwendung nötige Wissen Erwähnung findet. Die Modellierung umfasst dabei sowohl die Systemkomponente, die Verknüpfungen zwischen sprachlichen Äußerungen und Handlungen herstellt – das Lernermodell –, als auch die Komponente, die sprachliche Äußerungen tätigt, bis die gewünschte Verknüpfung hergestellt wurde – das Lehrermodell samt Lernzielkontrolle.
Die Umsetzung des Modells per Software [19] erlaubt die weitere Diskussion anhand einer Simulation mit einigen Testdaten. Eine ausführliche mathematische Analyse zeigt beweisbare Eigenschaften des Modells auf. Knappe Vergleiche mit der kybernetischen Didaktik nach von Cube [26] sowie der Suggestopädie Lozanovs [16] ordnen das Modell darüber hinaus noch in einen pädagogischen Kontext ein.