Reinforcement Learning of Minimalist Numeral Grammars

Graben, Peter beim; Römer, Ronald; Meyer, Werner; Huber, Markus; Wolff, Matthias

doi:10.1109/coginfocom47531.2019.9089924

Cited by 5 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the present study we have continued our work on language aquisition and on the unified description of physical interaction and linguistic communication of cognitive agents (Römer et al, 2019;beim Graben et al, 2020). The requirements for a unified description are primarily given by cognitive architectures.…”

Section: Discussionmentioning

confidence: 96%

“…Thus, a further aim of our work is the description of an algorithm with which a mental lexicon can be learned and dynamically updated through reinforcement learning. Starting point of our algorithm are utterance meaning pairs (Kwiatkowski et al, 2012;Wirsching and Lorenz, 2013;beim Graben et al, 2019b).…”

Section: Problem Statement and Experimental Setupmentioning

confidence: 99%

“…A sequence of signs "q" is called a minimalist expression. For further details we refer to beim Graben et al (2019b). We just repeat the two kinds of structure-building rules here.…”

Section: Minimalist Grammarsmentioning

confidence: 99%

“…According to Pinker (1995) this could substantially be avoided through reinforcement learning (Skinner, 2015;Sutton and Barto, 2018). Although there is only little psycholinguistic evidence for reinforcement learning in human language acquisition (Moerk, 1983;Sundberg et al, 1996), we outline a machine learning algorithm for the acquisition of an MG mental lexicon (beim Graben et al, 2020) of the syntax and semantics for English declarative sentences through reinforcement learning in this article. Our approach chosen here is inspired by similar work on linguistic reinforcement learning (Zettlemoyer and Collins, 2005;Kwiatkowski et al, 2012;Artzi and Zettlemoyer, 2013).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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: Discussionmentioning

confidence: 96%

Section: Problem Statement and Experimental Setupmentioning

confidence: 99%

“…A sequence of signs "q" is called a minimalist expression. For further details we refer to beim Graben et al (2019b). We just repeat the two kinds of structure-building rules here.…”

Section: Minimalist Grammarsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

“…Our classifications follow: Prospective - [68], [71]; Observational - [45], [46], [50], [59], [61], [63], [64]; Experimental - [43], [58], [60]; Technological - [44], [49], [51]- [54], [56], [62], [67]; Psychoanalytical - [55], [65], [66], [69], [70], [72]; Philosophical - [1], [42], [47], [48], [57]. 8 It may be observed that a range of methods are attested.…”

Section: Observing Interaction Analysis Paradigmsmentioning

confidence: 99%