The standard approach to model how human beings understand natural languages is the symbolic, compositional approach according to which the meaning of a complex expression is a function of the meanings of its constituents. In other words, meaning plays a fundamental role in the model. In this work, because of the polysemous, flexible, dynamic, and contextual structure of natural languages, this approach is rejected. Instead, a connectionist model which eliminates the concept of meaning is proposed.

In this paper, we explore interaction history as a particular source of pressure for achieving emergent compositional communication in multi-agent systems. We propose a training regime implementing template transfer, the idea of carrying over learned biases across contexts. In the presented method, a sender-receiver dyad is first trained with a disentangled pair of objectives, and then the receiver is transferred to train a new sender with a standard objective. Unlike other methods, the template transfer approach does not require imposing inductive (...) biases on the architecture of the agents. We experimentally show the emergence of compositional communication using topographical similarity, zero-shot generalization and context-independence as evaluation metrics. The presented approach is connected to an important line of work in semiotics and developmental psycholinguistics: it supports a conjecture that compositional communication is scaffolded on simpler communication protocols. (shrink)

Deep learning techniques have revolutionised artificial systems’ performance on myriad tasks, from playing Go to medical diagnosis. Recent developments have extended such successes to natural language processing, an area once deemed beyond such systems’ reach. Despite their different goals, these successes have suggested that such systems may be pertinent to theoretical linguistics. The competence/performance distinction presents a fundamental barrier to such inferences. While DL systems are trained on linguistic performance, linguistic theories are aimed at competence. Such a barrier has traditionally (...) been sidestepped by assuming a fairly close correspondence: performance as competence plus noise. I argue this assumption is unmotivated. Competence and performance can differ arbitrarily. Thus, we should not expect DL models to illuminate linguistic theory. (shrink)

The temporal structure of behavior contains a rich source of information about its dynamic organization, origins, and development. Today, advances in sensing and data storage allow researchers to collect multiple dimensions of behavioral data at a fine temporal scale both in and out of the laboratory, leading to the curation of massive multimodal corpora of behavior. However, along with these new opportunities come new challenges. Theories are often underspecified as to the exact nature of these unfolding interactions, and psychologists have (...) limited ready-to-use methods and training for quantifying structures and patterns in behavioral time series. In this paper, we will introduce four techniques to interpret and analyze high-density multi-modal behavior data, namely, to: (1) visualize the raw time series, (2) describe the overall distributional structure of temporal events (Burstiness calculation), (3) characterize the nonlinear dynamics over multiple timescales with Chromatic and Anisotropic Cross-Recurrence Quantification Analysis (CRQA), (4) and quantify the directional relations among a set of interdependent multimodal behavioral variables with Granger Causality. Each technique is introduced in a module with conceptual background, sample data drawn from empirical studies and ready-to-use Matlab scripts. The code modules showcase each technique’s application with detailed documentation to allow more advanced users to adapt them to their own datasets. Additionally, to make our modules more accessible to beginner programmers, we provide a “Programming Basics” module that introduces common functions for working with behavioral timeseries data in Matlab. Together, the materials provide a practical introduction to a range of analyses that psychologists can use to discover temporal structure in high-density behavioral data. (shrink)

The present paper intends to draw the conception of language implied in the technique of word embeddings that supported the recent development of deep neural network models in computational linguistics. After a preliminary presentation of the basic functioning of elementary artificial neural networks, we introduce the motivations and capabilities of word embeddings through one of its pioneering models, word2vec. To assess the remarkable results of the latter, we inspect the nature of its underlying mechanisms, which have been characterized as the (...) implicit factorization of a word-context matrix. We then discuss the ordinary association of the “distributional hypothesis” with a “use theory of meaning,” often justifying the theoretical basis of word embeddings, and contrast them to the theory of meaning stemming from those mechanisms through the lens of matrix models (such as vector space models and distributional semantic models). Finally, we trace back the principles of their possible consistency through Harris’s original distributionalism up to the structuralist conception of language of Saussure and Hjelmslev. Other than giving access to the technical literature and state of the art in the field of natural language processing to non-specialist readers, the paper seeks to reveal the conceptual and philosophical stakes involved in the recent application of new neural network techniques to the computational treatment of language. (shrink)

Many of the computing systems programmed using Machine Learning are opaque: it is difficult to know why they do what they do or how they work. Explainable Artificial Intelligence aims to develop analytic techniques that render opaque computing systems transparent, but lacks a normative framework with which to evaluate these techniques’ explanatory successes. The aim of the present discussion is to develop such a framework, paying particular attention to different stakeholders’ distinct explanatory requirements. Building on an analysis of “opacity” from (...) philosophy of science, this framework is modeled after accounts of explanation in cognitive science. The framework distinguishes between the explanation-seeking questions that are likely to be asked by different stakeholders, and specifies the general ways in which these questions should be answered so as to allow these stakeholders to perform their roles in the Machine Learning ecosystem. By applying the normative framework to recently developed techniques such as input heatmapping, feature-detector visualization, and diagnostic classification, it is possible to determine whether and to what extent techniques from Explainable Artificial Intelligence can be used to render opaque computing systems transparent and, thus, whether they can be used to solve the Black Box Problem. (shrink)

This paper proposes several recurrent neural network-based models for recognizing requisite and effectuation parts in Legal Texts. Firstly, we propose a modification of BiLSTM-CRF model that allows the use of external features to improve the performance of deep learning models in case large annotated corpora are not available. However, this model can only recognize RE parts which are not overlapped. Secondly, we propose two approaches for recognizing overlapping RE parts including the cascading approach which uses the sequence of BiLSTM-CRF models (...) and the unified model approach with the multilayer BiLSTM-CRF model and the multilayer BiLSTM-MLP-CRF model. Experimental results on two Japan law RRE datasets demonstrated advantages of our proposed models. For the Japanese National Pension Law dataset, our approaches obtained an \ score of 93.27% and exhibited a significant improvement compared to previous approaches. For the Japan Civil Code RRE dataset which is written in English, our approaches produced an \ score of 78.24% in recognizing RE parts that exhibited a significant improvement over strong baselines. In addition, using external features and in-domain pre-trained word embeddings also improved the performance of RRE systems. (shrink)

Neurological syndromes in which consciousness seems to malfunction, such as temporal lobe epilepsy, visual scotomas, Charles Bonnet syndrome, and synesthesia offer valuable clues about the normal functions of consciousness and ‘qualia’. An investigation into these syndromes reveals, we argue, that qualia are different from other brain states in that they possess three functional characteristics, which we state in the form of ‘three laws of qualia’. First, they are irrevocable: I cannot simply decide to start seeing the sunset as green, or (...) feel pain as if it were an itch; second, qualia do not always produce the same behaviour: given a set of qualia, we can choose from a potentially infinite set of possible behaviours to execute; and third, qualia endure in short-term memory, as opposed to non-conscious brain states involved in the on-line guidance of behaviour in real time. We suggest that qualia have evolved these and other attributes because of their role in facilitating non-automatic, decision-based action. We also suggest that the apparent epistemic barrier to knowing what qualia another person is experiencing can be overcome by using a ‘bridge’ of neurons; and we offer a hypothesis about the relation between qualia and one's sense of self. (shrink)

Ten years ago, researchers using event-related brain potentials to study language comprehension were puzzled by what looked like a Semantic Illusion: Semantically anomalous, but structurally well-formed sentences did not affect the N400 component—traditionally taken to reflect semantic integration—but instead produced a P600 effect, which is generally linked to syntactic processing. This finding led to a considerable amount of debate, and a number of complex processing models have been proposed as an explanation. What these models have in common is that they (...) postulate two or more separate processing streams, in order to reconcile the Semantic Illusion and other semantically induced P600 effects with the traditional interpretations of the N400 and the P600. Recently, however, these multi-stream models have been called into question, and a simpler single-stream model has been proposed. According to this alternative model, the N400 component reflects the retrieval of word meaning from semantic memory, and the P600 component indexes the integration of this meaning into the unfolding utterance interpretation. In the present paper, we provide support for this “Retrieval–Integration ” account by instantiating it as a neurocomputational model. This neurocomputational model is the first to successfully simulate the N400 and P600 amplitude in language comprehension, and simulations with this model provide a proof of concept of the single-stream RI account of semantically induced patterns of N400 and P600 modulations. (shrink)

This paper introduces a special issue of Cognitive Science initiated on the 25th anniversary of the publication of Parallel Distributed Processing (PDP), a two-volume work that introduced the use of neural network models as vehicles for understanding cognition. The collection surveys the core commitments of the PDP framework, the key issues the framework has addressed, and the debates the framework has spawned, and presents viewpoints on the current status of these issues. The articles focus on both historical roots and contemporary (...) developments in learning, optimality theory, perception, memory, language, conceptual knowledge, cognitive control, and consciousness. Here we consider the approach more generally, reviewing the original motivations, the resulting framework, and the central tenets of the underlying theory. We then evaluate the impact of PDP both on the field at large and within specific subdomains of cognitive science and consider the current role of PDP models within the broader landscape of contemporary theoretical frameworks in cognitive science. Looking to the future, we consider the implications for cognitive science of the recent success of machine learning systems called “deep networks”—systems that build on key ideas presented in the PDP volumes. (shrink)

The computational paradigm, which has dominated psychology and artificial intelligence since the cognitive revolution, has been a source of intense debate. Recently, several cognitive scientists have argued against this paradigm, not by objecting to computation, but rather by objecting to the notion of representation. Our analysis of these objections reveals that it is not the notion of representation per se that is causing the problem, but rather specific properties of representations as they are used in various psychological theories. Our analysis (...) suggests that all theorists accept the idea that cognitive processing involves internal information-carrying states that mediate cognitive processing. These mediating states are a superordinate category of representations. We discuss five properties that can be added to mediating states and examine their importance in various cognitive models. Finally, three methodological lessons are drawn from our analysis and discussion. (shrink)

[Edited from Conclusion section:] We have looked at various challenging issues to do with getting connectionism to cope with high-level cognitive activities such a reasoning and natural language understanding. The issues are to do with various facets of generalization that are not commonly noted. We have been concerned in particular with the special forms these issues take in the arena of propositional attitude processing. The main problems we have looked at are: (1) The need to construct explicit representations of generalizations, (...) not just generalize correctly to individual cases; (2) The need to be able to match two or more complex short-term information structures, to enable rapid generalization from recent examples rather than from long-term memories; (3) The need to represent and reason with anomalous combinations of concepts; (4) The need to perform embedded reasoning. This presents special problems for systems using non-concatenative representations (as in mainstream connectionist approaches). We also touched on vague quantification in attitude report complements. Neither this topic nor that of analogies between short-term structures (point 2) has been adequately addressed in the symbolic framework, let alone in connectionism. -/- The opportunities and problems covered are put forward as things worth being optimistic about or pessimistic about, respectively. They are not put forward as decisive arguments for or against connectionism. The hope is that this chapter contributes to a greater understanding of the connectionist/symbolist gap by presenting some unusual issues and by throwing new light on some well known ones. (shrink)

Recent work in the methodology of connectionist explanation has I'ocrrsccl on the notion of levels of explanation. Specific issucs in conncctionisrn hcrc intersect with rvider areas of debate in the philosophy of psychology and thc philosophy of science generally. The issues I raise in this chapter, then, are not unique to cognitive science; but they arise in new and important contexts when connectionism is taken seriously as a model of cognition. The general questions are the relation between levels and the (...) status of levels which have no obvious relation to others. In speaking of levels, what is the connection, if there is one, between explanation and ontology? Which, if any, conccpt of reduction is applicable to connectionist systems? What kind of legitinrtcy can the constructs of common sense psychology, or of that vclsion ol intentional realism represented by classical symbol-systems n I, hirvc irr ir full-scale connectionist theory of mind? (shrink)

Converging data from different disciplines are showing the role of classical conditioning processes in the elaboration of human and animal behavior to be larger than previously supposed. Restricted views of classically conditioned responses as merely secretory, reflexive, or emotional are giving way to a broader conception that includes problem-solving, and other rule-governed behavior thought to be the exclusive province of either operant conditiońing or cognitive psychology. These new views have been accompanied by changes in the way conditioning is conducted and (...) evaluated. Data from a number of seemingly unrelated phenomena such as relapse to drug abuse by postaddicts, the placebo effect, and the immune response appear to involve classical conditioning processes. Classical conditioning, moreover, has been found to occur in simpler and simpler organisms and recently even demonstrated in brain slices and in utero. This target article will integrate the several research areas that have used the classical conditioning process as an explanatory model; it will challenge teleological interpretations of the classically conditioned CR and offer some basic principles for testing conditioning in diverse areas. (shrink)

An essential aspect of knowing language is knowing the words of that language. This knowledge is usually thought to reside in the mental lexicon, a kind of dictionary that contains information regarding a word’s meaning, pronunciation, syntactic characteristics, and so on. In this article, a very different view is presented. In this view, words are understood as stimuli that operate directly on mental states. The phonological, syntactic and semantic properties of a word are revealed by the effects it has on (...) those states. (shrink)

It has been suggested that the enterprise of developing mechanistic theories of the human cognitive architecture is flawed because the theories produced are not directly falsifiable. Newell attempted to sidestep this criticism by arguing for a Lakatosian model of scientific progress in which cognitive architectures should be understood as theories that develop over time. However, Newell's own candidate cognitive architecture adhered only loosely to Lakatosian principles. This paper reconsiders the role of falsification and the potential utility of Lakatosian principles in (...) the development of cognitive architectures. It is argued that a lack of direct falsifiability need not undermine the scientific development of a cognitive architecture if broadly Lakatosian principles are adopted. Moreover, it is demonstrated that the Lakatosian concepts of positive and negative heuristics for theory development and of general heuristic power offer methods for guiding the development of an architecture and for evaluating the contribution and potential of an architecture's research program. (shrink)

The poverty of stimulus argument is one of the most controversial arguments in the study of language acquisition. Here we follow previous approaches challenging the assumption of impoverished primary linguistic data, focusing on the specific problem of auxiliary (AUX) fronting in complex polar interrogatives. We develop a series of corpus analyses of child-directed speech showing that there is indirect statistical information useful for correct auxiliary fronting in polar interrogatives and that such information is sufficient for distinguishing between grammatical and ungrammatical (...) generalizations, even in the absence of direct evidence. We further show that there are simple learning devices, such as neural networks, capable of exploiting such statistical cues, producing a bias toward correct AUX questions when compared to their ungrammatical counterparts. The results suggest that the basic assumptions of the poverty of stimulus argument may need to be reappraised. (shrink)

Talk of linguistic universals has given cognitive scientists the impression that languages are all built to a common pattern. In fact, there are vanishingly few universals of language in the direct sense that all languages exhibit them. Instead, diversity can be found at almost every level of linguistic organization. This fundamentally changes the object of enquiry from a cognitive science perspective. This target article summarizes decades of cross-linguistic work by typologists and descriptive linguists, showing just how few and unprofound the (...) universal characteristics of language are, once we honestly confront the diversity offered to us by the world's 6,000 to 8,000 languages. After surveying the various uses of “universal,” we illustrate the ways languages vary radically in sound, meaning, and syntactic organization, and then we examine in more detail the core grammatical machinery of recursion, constituency, and grammatical relations. Although there are significant recurrent patterns in organization, these are better explained as stable engineering solutions satisfying multiple design constraints, reflecting both cultural-historical factors and the constraints of human cognition.Linguistic diversity then becomes the crucial datum for cognitive science: we are the only species with a communication system that is fundamentally variable at all levels. Recognizing the true extent of structural diversity in human language opens up exciting new research directions for cognitive scientists, offering thousands of different natural experiments given by different languages, with new opportunities for dialogue with biological paradigms concerned with change and diversity, and confronting us with the extraordinary plasticity of the highest human skills. (shrink)

The entropy-reduction hypothesis claims that the cognitive processing difficulty on a word in sentence context is determined by the word's effect on the uncertainty about the sentence. Here, this hypothesis is tested more thoroughly than has been done before, using a recurrent neural network for estimating entropy and self-paced reading for obtaining measures of cognitive processing load. Results show a positive relation between reading time on a word and the reduction in entropy due to processing that word, supporting the entropy-reduction (...) hypothesis. Although this effect is independent from the effect of word surprisal, we find no evidence that these two measures correspond to cognitively distinct processes. (shrink)

Understanding the role of ‘‘representations’’ in cognitive science is a fundamental problem facing the emerging framework of embodied, situated, dynamical cognition. To make progress, I follow the approach proposed by an influential representational skeptic, Randall Beer: building artificial agents capable of minimally cognitive behaviors and assessing whether their internal states can be considered to involve representations. Hence, I operationalize the concept of representing as ‘‘standing in,’’ and I look for representations in embodied agents involved in simple categorization tasks. In a (...) first experiment, no representation can be found, but the relevance of the task is undermined by the fact that agents with no internal states can reach high performance. A simple modification makes the task more “representationally hungry,” and in this case, agents’ internal states are found to qualify as representations. I conclude by discussing the benefits of reconciling the embodied-dynamical approach with the notion of representation. (shrink)