Despite its strengths, Leech et al.'s model fails to address the important benefits that derive from self-explanation and task feedback in analogical reasoning development. These components encourage explicit, self-reflective processes that do not necessarily link to knowledge accretion. We wonder, therefore, what mechanisms can be included within a connectionist framework to model self-reflective involvement and its beneficial consequences.

This contribution presents a corpus of spatial descriptions and describes the development of a human-driven spatial language robot system for their comprehension. The domain of application is an eldercare setting in which an assistive robot is asked to “fetch” an object for an elderly resident based on a natural language spatial description given by the resident. In Part One, we describe a corpus of naturally occurring descriptions elicited from a group of older adults within a virtual 3D home that simulates (...) the eldercare setting. We contrast descriptions elicited when participants offered descriptions to a human versus robot avatar, and under instructions to tell the addressee how to find the target versus where the target is. We summarize the key features of the spatial descriptions, including their dynamic versus static nature and the perspective adopted by the speaker. In Part Two, we discuss critical cognitive and perceptual processing capabilities necessary for the robot to establish a common ground with the human user and perform the “fetch” task. Based on the collected corpus, we focus here on resolving the perspective ambiguity and recognizing furniture items used as landmarks in the descriptions. Taken together, the work presented here offers the key building blocks of a robust system that takes as input natural spatial language descriptions and produces commands that drive the robot to successfully fetch objects within our eldercare scenario. (shrink)

Space can be understood through perception and language, but are the processes that represent spatial information the same in both cases? This paper reviews psychological evidence for the functional equivalence of spatial representations based on perceptual and linguistic inputs. It is proposed that spatial information is processed by a specialised spatial representation system (SRS) that creates geometric representations of space. The SRS receives inputs from perceptual and linguistic systems and uses these basic inputs to construct mental spatial models of the (...) observed or described environment. A mental spatial model is created by determining the coordinate locations of objects in the egocentric or allocentric frame of reference. The goal of the SRS is not to represent strictly what is perceived, but to model an environment that has an inherent three‐dimensional spatial structure. (shrink)

Space can be understood through perception and language, but are the processes that represent spatial information the same in both cases? This paper reviews psychological evidence for the functional equivalence of spatial representations based on perceptual and linguistic inputs. It is proposed that spatial information is processed by a specialised spatial representation system (SRS) that creates geometric representations of space. The SRS receives inputs from perceptual and linguistic systems and uses these basic inputs to construct mental spatial models of the (...) observed or described environment. A mental spatial model is created by determining the coordinate locations of objects in the egocentric or allocentric frame of reference. The goal of the SRS is not to represent strictly what is perceived, but to model an environment that has an inherent three‐dimensional spatial structure. (shrink)

Speech disfluencies can signal that a speaker is about to refer to something difficult to name. In two experiments, we found evidence that 4-year-olds, like adults, flexibly interpret a particular partner’s disfluency based on their estimate of that partner’s knowledge, derived from the preceding conversation. In entrainment trials, children established partner-specific shared knowledge of names for tangram pictures with one or two adult interlocutors. In each test trial, an adult named one of two visible tangrams either fluently or disfluently while (...) children’s eye-movements were monitored. We manipulated speaker knowledge in the test trials. In Experiment 1, the test-trial speaker was the same speaker from entrainment or a naïve experimenter; in Experiment 2, the test-trial speaker had been one of the child’s partners in entrainment and had seen half of the tangrams. When hearing disfluent expressions, children looked more at a tangram that was unfamiliar from the speaker’s perspective; this systematic disfluency effect disappeared in Experiment 1 when the speaker was entirely naïve, and depended on each speaker’s entrainment experience in Experiment 2. These findings show that 4-year-olds can keep track of two different partners’ knowledge states, and use this information to determine what should be difficult for a particular partner to name, doing so efficiently enough to guide online interpretation of disfluent speech. (shrink)

Communicating with multiple addressees poses a problem for speakers: Each addressee necessarily comes to the conversation with a different perspective—different knowledge, different beliefs, and a distinct physical context. Despite the ubiquity of multiparty conversation in everyday life, little is known about the processes by which speakers design language in multiparty conversation. While prior evidence demonstrates that speakers design utterances to accommodate addressee knowledge in multiparty conversation, it is unknown if and how speakers encode and combine different types of perspective information. (...) Here we test whether speakers encode the perspective of multiple addressees, and then simultaneously consider their knowledge and physical context during referential design in a three‐party conversation. Analyses of referential form—expression length, disfluency, and elaboration rate—in an interactive multiparty conversation demonstrate that speakers do take into consideration both addressee knowledge and physical context when designing utterances, consistent with a knowledge‐scene integration view. These findings point to an audience design process that takes as input multiple types of representations about the perspectives of multiple addressees, and that bases the informational content of the to‐be‐designed utterance on a combination of the perspectives of the intended addressees. (shrink)

Spatial communications are essential to the survival and social interaction of human beings. In science fiction and the near future, robots are supposed to be able to understand spatial languages to collaborate and cooperate with humans. However, it remains unknown whether human speakers regard robots as human-like social partners. In this study, human speakers describe target locations to an imaginary human or robot addressee under various scenarios varying in relative speaker–addressee cognitive burden. Speakers made equivalent perspective choices to human and (...) robot addressees, which consistently shifted according to the relative speaker–addressee cognitive burden. However, speakers’ perspective choice was only significantly correlated to their social skills when the addressees were humans but not robots. These results suggested that people generally assume robots and humans with equal capabilities in understanding spatial descriptions but do not regard robots as human-like social partners. (shrink)

It makes sense that the more information people share, the better they communicate. To evaluate the effect of knowledge overlap on the effectiveness of communication, participants played a communication game where the “director” identified objects to the “addressee”. Pairs either shared information about most objects' names (high overlap), or about the minority of objects' names (low overlap). We found that high-overlap directors tended to use more names than low overlap directors. High overlap directors also used more names with objects whose (...) names only they knew, thereby confusing their addressees more often than low-overlap directors. We conclude that while sharing more knowledge can be beneficial to communication overall, it can cause communication to be locally ineffective. Sharing more information reduces communication effectiveness precisely when there is an opportunity to inform—when people communicate information only they themselves know. (shrink)

Although people can take spatial perspectives different from their own, it is widely assumed that egocentric perspectives are natural and have primacy. Two studies asked respondents to describe the spatial relations between two objects on a table in photographed scenes; in some versions, a person sitting behind the objects was either looking at or reaching for one of the objects. The mere presence of another person in a position to act on the objects induced a good proportion of respondents to (...) describe the spatial relations from that person’s point of view. When the query about the spatial relations was phrased in terms of action, more respondents took the other’s perspective than their own. The implication of action elicits spontaneous spatial perspective-taking, seemingly in the service of understanding the other’s actions. (shrink)

The mind constructs narratives from what would otherwise be chaos. Narratives viewed minimally—at least two temporally ordered events—are revealed in the way people talk about space and time. Narratives replete with a voice, causality, and emotion are reflected in the stories people tell about their own lives, stories that, as acknowledged by their tellers, distort the details around 60% of the time, but, according to their tellers, distort the 'truth' far less often.

We investigated the coupling between a speaker's and a listener's eye movements. Some participants talked extemporaneously about a television show whose cast members they were viewing on a screen in front of them. Later, other participants listened to these monologues while viewing the same screen. Eye movements were recorded for all speakers and listeners. According to cross-recurrence analysis, a listener's eye movements most closely matched a speaker's eye movements at a delay of 2 sec. Indeed, the more closely a listener's (...) eye movements were coupled with a speaker's, the better the listener did on a comprehension test. In a second experiment, low-level visual cues were used to manipulate the listeners' eye movements, and these, in turn, influenced their latencies to comprehension questions. Just as eye movements reflect the mental state of an individual, the coupling between a speaker's and a listener's eye movements reflects the success of their communication. (shrink)

Theoretical and empirical contributions to the understanding of communicative interactions between heterospecifics are scarce and tend to apply a monological model of communication that focuses on the transfer of information from signallers to receivers. This study relies on an alternative model of communication, semiotic alignment, which sees communicative interaction as a dialogical process of joint semiosis resulting in the alignment of the interactants’ own-worlds. We conducted an experiment where dyads composed of an elephant instruction-giver and a human instruction-receiver needed to (...) engage in dynamic and interactive communication in order to solve a cooperative object-choice task. Our results showed that dyads were able to solve the task well above chance levels. Moreover, cross-recurrence analysis revealed that interactants were synchronizing referential indexical gestures throughout the experiment. However, we were not able to confirm a direct correlation between joint deixis and experimental outcomes, presumably because these outcomes are dependent on other forms of joint semiosis not analysed in this study. (shrink)

The authors' claim that analogical reasoning is the product of relational priming is compatible with language processing work that emphasizes the role of low-level automatic processes in the alignment of situation models in dialogue. However, their model ignores recent behavioral evidence demonstrating a effect on relational priming. We discuss implications of these data.

Traditional mechanistic accounts of language processing derive almost entirely from the study of monologue. Yet, the most natural and basic form of language use is dialogue. As a result, these accounts may only offer limited theories of the mechanisms that underlie language processing in general. We propose a mechanistic account of dialogue, the interactive alignment account, and use it to derive a number of predictions about basic language processes. The account assumes that, in dialogue, the linguistic representations employed by the (...) interlocutors become aligned at many levels, as a result of a largely automatic process. This process greatly simplifies production and comprehension in dialogue. After considering the evidence for the interactive alignment model, we concentrate on three aspects of processing that follow from it. It makes use of a simple interactive inference mechanism, enables the development of local dialogue routines that greatly simplify language processing, and explains the origins of self-monitoring in production. We consider the need for a grammatical framework that is designed to deal with language in dialogue rather than monologue, and discuss a range of implications of the account. Key Words: common ground; dialogue; dialogue routines; language comprehension; language production; monitoring; perception-behavior link. (shrink)

This study examines the sequential and situated organization associated with framing locational formulations by dislocated parties to mobile phone calls for the joint accomplishment of location-related social action. The data come from 22 mundane Farsi mobile phone calls involving location inquiring and/or reporting. The analysis of the data, informed by conversational analysis and Levinson’s conceptual framework of perspective-taking, adds frame of reference to Schegloff’s location, membership, and topic or activity analyses operative in the selection of locational formulations. The trajectory plotted (...) for location-related action indicates the contingent roles which material, linguistic and semiotic resources play in the selection of locational formulations deployed for co-presence purposes. The findings suggest consequentiality of the-relevant-next action for the framing of locational descriptions and provide insight into how conversationalists interact with their physical environment in a wider social context. (shrink)

Integrating different perspectives is a sophisticated strategy for developing constructive interactions in collaborative problem solving. However, cognitive aspects such as individuals’ knowledge and bias often obscure group consensus and produce conflict. This study investigated collaborative problem solving, focusing on a group member interacting with another member having a different perspective. It was predicted that mavericks might mitigate disadvantages and facilitate perspective taking during problem solving. Thus, 344 university students participated in two laboratory-based experiments by engaging in a simple rule-discovery task (...) that raised conflicts among perspectives. They interacted with virtual partners whose conversations were controlled by multiple conversational agents. Results show that when participants interacted with a maverick during the task, they were able to take others’ perspectives and integrate different perspectives to solve the problem. Moreover, when participants interacted in groups with a positive mood, groups with a maverick outperformed groups having several perspectives. (shrink)

Recent debates over adults' theory of mind use have been fueled by surprising failures of perspective-taking in communication, suggesting that perspective-taking may be relatively effortful. Yet adults routinely engage in effortful processes when needed. How, then, should speakers and listeners allocate their resources to achieve successful communication? We begin with the observation that the shared goal of communication induces a natural division of labor: The resources one agent chooses to allocate toward perspective-taking should depend on their expectations about the other's (...) allocation. We formalize this idea in a resource-rational model augmenting recent probabilistic weighting accounts with a mechanism for (costly) control over the degree of perspective-taking. In a series of simulations, we first derive an intermediate degree of perspective weighting as an optimal trade-off between expected costs and benefits of perspective-taking. We then present two behavioral experiments testing novel predictions of our model. In Experiment 1, we manipulated the presence or absence of occlusions in a director–matcher task. We found that speakers spontaneously modulated the informativeness of their descriptions to account for “known unknowns” in their partner's private view, reflecting a higher degree of speaker perspective-taking than previously acknowledged. In Experiment 2, we then compared the scripted utterances used by confederates in prior work with those produced in interactions with unscripted directors. We found that confederates were systematically less informative than listeners would initially expect given the presence of occlusions, but listeners used violations to adaptively make fewer errors over time. Taken together, our work suggests that people are not simply “mindblind”; they use contextually appropriate expectations to navigate the division of labor with their partner. We discuss how a resource-rational framework may provide a more deeply explanatory foundation for understanding flexible perspective-taking under processing constraints. (shrink)

We examined how social cues and representational ones jointly shape people's spatial memory representations and their subsequent descriptions. In 24 pairs, Directors studied an array with a symmetrical structure while either knowing their Matcher's subsequent viewpoint or not. During the subsequent description of the array, the array's intrinsic structure was aligned with the Director, the Matcher, or neither partner. According to memory tests preceding descriptions, Directors who had studied the array while aligned with its structure were more likely to use (...) its orientation as an organizing direction. Directors who had studied the array while misaligned with its structure used its orientation more frequently as an organizing orientation when knowing that the Matcher would be aligned with it, but used their own viewpoint more frequently as an organizing direction when not knowing the Matcher's viewpoint. Directors also adapted their descriptions strategically, using more egocentric expressions when aligned with the intrinsic structure and more partner-centered expressions when their Matchers were the ones aligned with the structure, even when this information wasn't available in advance. These findings suggest that speakers are guided by converging social and representational cues to adapt flexibly the organization of their memories and the perspectives of their descriptions. (shrink)

Drawing on a corpus of eight task-based interactions involving a map task ), this article seeks to focus on how speakers orient to directional terms in an interactional context, and in so doing, to add to features that can be deemed to characterize this speech exchange system. Analysis of the data using conversation analysis showed that features of the talk were confirmation and clarification checks, which provided an opportunity to check understanding and the accuracy of the instruction leading to a (...) correction, acknowledgement or further information; modulated repair and mitigated criticism, resulting in the maintenance of an affiliative stance towards the other speaker; and avoidance of problems that viewpoints or directional terms might cause. Problems with the directional terms in this corpus confirm prior research that the confusion between east and west, and left and right are the terms that cause problems for speakers. (shrink)

Cultural evolutionary theory has identified a range of cognitive biases that guide human social learning. Naturalistic and experimental studies indicate transmission biases favoring negative and positive information. To address these conflicting findings, the present study takes a socially situated view of information transmission, which predicts that bias expression will depend on the social context. We report a large‐scale experiment (N = 425) that manipulated the social context and examined its effect on the transmission of the positive and negative information contained (...) in a narrative text. In each social context, information was progressively lost as it was transmitted from person to person, but negative information survived better than positive information, supporting a negative transmission bias. Importantly, the negative transmission bias was moderated by the social context: Higher social connectivity weakened the bias to transmit negative information, supporting a socially situated account of information transmission. Our findings indicate that our evolved cognitive preferences can be moderated by our social goals. (shrink)

We investigate partner effects on spatial perspective taking behavior in listeners, comparing behavior with a human versus a computer partner (Experiments 1 and 2), and with computer partners of different perceived capabilities (Experiment 3). Participants responded to spoken instructions from their partner which could be interpreted egocentrically (from their own perspective) or othercentrically (from their partner's perspective). In contrast to earlier work, we found that participants were more egocentric with a computer than a human partner. Participants were also more egocentric (...) with a computer partner that appeared more modern and capable, compared to one that appeared outdated and limited in ability. Our results show that perspective taking behavior is sensitive to information about one's partner; in particular, listeners consider their partner's potential ability to collaborate, adjusting their egocentric tendencies accordingly. Moreover, we highlight what appears to be a shift in listeners' expectations regarding computers' collaborative capabilities, leading to greater willingness to push the burden of perspective taking onto a computer partner. (shrink)

In a matter of mere milliseconds, conversational partners can transform their expectations about the world in a way that accords with another person's perspective. At the same time, in similar situations, the exact opposite also appears to be true. Rather than being at odds, these findings suggest that there are multiple contextual and processing constraints that may guide when and how people consider perspective. These constraints are shaped by a host of factors, including the availability of social and environmental cues, (...) and intrinsic biases and cognitive abilities. To explain how these might be integrated in a new way forward, we turn to an adaptive account of interpersonal interaction. This account draws from basic principles of dynamical systems, principles that we argue are already expressed, both implicitly and explicitly, within a broad landscape of existing research. We then showcase an initial attempt to develop a computational framework to instantiate some of these principles. This framework, consisting of what we argue to be important mechanistic insights rendered by neural network models, is based on a promising and long-standing approach that has yet to take hold in the current domain. We argue that by bridging this gap, new insights into other theoretical accounts, such as the connections between memory and common ground information, might be revealed. (shrink)

Leech et al.'s model proposes representing relations as primed transformations rather than as structured representations (explicit representations of relations and their roles dynamically bound to fillers). However, this renders the model unable to explain several developmental trends (including relational integration and all changes not attributable to growth in relational knowledge). We suggest looking to an alternative computational model that learns structured representations from examples.

Paulina Sliwa (2015) argues that knowing why p is necessary and sufficient for understanding why p. She tries to rebut recent attacks against the necessity and sufficiency claims, and explains the gradability of understanding why in terms of knowledge. I argue that her attempts do not succeed, but I indicate more promising ways to defend reductionism about understanding why throughout the discussion.