The development of reasoning systems exploiting expert knowledge from interactions with humans is a non-trivial problem, particularly when considering how the information can be coded in the knowledge representation. For example, in human development, the acquisition of knowledge at one level requires the consolidation of knowledge from lower levels. How is the accumulated experience structured to allow the individual to apply knowledge to new situations, allowing reasoning and adaptation? We investigate how this can be done automatically by an iCub that (...) interacts with humans to acquire knowledge via demonstration. Once consolidated, this knowledge is used in further acquisitions of experience concerning preconditions and consequences of actions. Finally, this knowledge is translated into rules that allow reasoning and planning for novel problem solving, including a Tower of Hanoi scenario. We thus demonstrate proof of concept for an interaction system that uses knowledge acquired from human interactions to reason about new situations. (shrink)

The dualist / materialist debates about the nature of consciousness are based on the assumption that an entirely physical universe must ultimately be observable by humans (with infinitely advanced tools). Thus the dualists claim that anything unobservable must be non-physical, while the materialists argue that in theory nothing is unobservable. However, there may be fundamental limitations in the power of human observation, no matter how well aided, that greatly curtail our ability to know and observe even a fully physical universe. (...) This paper presents arguments to support the model of an inherently limited observer and explores the consequences of this view. (shrink)

Models of category learning have been extensively studied in cognitive science and primarily tested on perceptual abstractions or artificial stimuli. In this paper, we focus on categories acquired from natural language stimuli, that is, words. We present a Bayesian model that, unlike previous work, learns both categories and their features in a single process. We model category induction as two interrelated subproblems: the acquisition of features that discriminate among categories, and the grouping of concepts into categories based on those features. (...) Our model learns categories incrementally using particle filters, a sequential Monte Carlo method commonly used for approximate probabilistic inference that sequentially integrates newly observed data and can be viewed as a plausible mechanism for human learning. Experimental results show that our incremental learner obtains meaningful categories which yield a closer fit to behavioral data compared to related models while at the same time acquiring features which characterize the learned categories. (shrink)

well-known arguments dispute the meaningfulness of language use in specific extant systems; the symbols they use..

Interdisciplinary investigations marry the methods and concerns of different fields. Computer science is the study of precise descriptions of finite processes; semantics is the study of meaning in language. Thus, computational semantics embraces any project that approaches the phenomenon of meaning by way of tasks that can be performed by following definite sets of mechanical instructions. So understood, computational semantics revels in applying semantics, by creating intelligent devices whose broader behavior fits the meanings of utterances, and not just their form. (...) IBM’s Watson (Ferrucci, Brown, Chu-Carroll, Fan, Gondek, Kalyanpur, Lally, Murdock, Nyberg, Prager, Schlaefer & Welty 2010) is a harbinger of the excitement and potential of this technology. (shrink)

We describe a methodology for learning a disambiguation model for deep pragmatic interpretations in the context of situated task-oriented dialogue. The system accumulates training examples for ambiguity resolution by tracking the fates of alternative interpretations across dialogue, including subsequent clarificatory episodes initiated by the system itself. We illustrate with a case study building maximum entropy models over abductive interpretations in a referential communication task. The resulting model correctly resolves 81% of ambiguities left unresolved by an initial handcrafted baseline. A key (...) innovation is that our method draws exclusively on a system’s own skills and experience and requires no human annotation. (shrink)

The reconciliation of theories of concepts based on prototypes, exemplars, and theory-like structures is a longstanding problem in cognitive science. In response to this problem, researchers have recently tended to adopt either hybrid theories that combine various kinds of representational structure, or eliminative theories that replace concepts with a more finely grained taxonomy of mental representations. In this paper, we describe an alternative approach involving a single class of mental representations called “semantic pointers.” Semantic pointers are symbol-like representations that result (...) from the compression and recursive binding of perceptual, lexical, and motor representations, effectively integrating traditional connectionist and symbolic approaches. We present a computational model using semantic pointers that replicates experimental data from categorization studies involving each prior paradigm. We argue that a framework involving semantic pointers can provide a unified account of conceptual phenomena, and we compare our framework to existing alternatives in accounting for the scope, content, recursive combination, and neural implementation of concepts. (shrink)

According to usage-based approaches to language acquisition, linguistic knowledge is represented in the form of constructions—form-meaning pairings—at multiple levels of abstraction and complexity. The emergence of syntactic knowledge is assumed to be a result of the gradual abstraction of lexically specific and item-based linguistic knowledge. In this article, we explore how the gradual emergence of a network consisting of constructions at varying degrees of complexity can be modeled computationally. Linguistic knowledge is learned by observing natural language utterances in an ambiguous (...) context. To determine meanings of constructions starting from ambiguous contexts, we rely on the principle of cross-situational learning. While this mechanism has been implemented in several computational models, these models typically focus on learning mappings between words and referents. In contrast, in our model, we show how cross-situational learning can be applied consistently to learn correspondences between form and meaning beyond such simple correspondences. (shrink)