Towards coping and imagination for cognitive agents

Wolff, Matthias; Römer, Ronald; Wirsching, Günther

doi:10.1109/coginfocom.2015.7390609

Cited by 7 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We consider the well-known mouse-maze problem (Shannon, 1953;Wolff et al, 2015Wolff et al, , 2018, where an artificial mouse lives in a simple N×M maze world that is given by a certain configuration of walls. For the mouse to survive, one ore more target objects are located at some places in the maze.…”

Section: Problem Statement and Experimental Setupmentioning

confidence: 99%

See 1 more Smart Citation

Unifying Physical Interaction, Linguistic Communication, and Language Acquisition of Cognitive Agents by Minimalist Grammars

Römer

Graben

Huber-Liebl

et al. 2022

Front. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Problem Statement and Experimental Setupmentioning

confidence: 99%

“…In semiotics, this process is called denotation and can be realized by a logical compound system (see Figure 4). If no matches are found, an adaptation or coping process is triggered (Wolff et al, 2015).…”

Section: Knowledge Integrationmentioning

confidence: 99%

Unifying Physical Interaction, Linguistic Communication, and Language Acquisition of Cognitive Agents by Minimalist Grammars

Römer

Graben

Huber-Liebl

et al. 2022

Front. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…One particular demand on cognitive user interfaces are the processing and understanding of declarative or imperative sentences. Consider, e.g., a speechcontrolled heating device, a cognitive heating [15,29,58,62,63], with the operator's utterance "I am cold!" This declarative sentence must firstly be analyzed syntactically to assigning "I" to the subject position and attributing "am cold" to the predicate.…”

Section: Introductionmentioning

confidence: 99%

“…From this representation of the speaker's state, the system must compute logical inferences and then respond accordingly, by increasing the room temperature and probably by giving a linguistic feedback signal "I increase the temperature to 22 degrees". Technically, this could be achieved using feature-value relations (FVR) [62] as semantic representations and modified Markov-decision processes (MDP) for behavior control [58,62,63].…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning of minimalist grammars

Graben,

Römer,

Meyer

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic slots to interpret the user's intent. In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a mental lexicon, comprising syntactic, phonetic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. We outline a reinforcement learning algorithm for the acquisition of syntax and semantics of English utterances, based on minimalist grammar (MG), a recent computational implementation of generative linguistics. 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.

show abstract