ConceptNet is a freely available commonsense knowledgebase and natural-language-processing toolkit which supports many practical textual-reasoning tasks over real-world documents including topic-jisting (e.g. a news article containing the concepts, "gun," "convenience store," "demand money" and "make getaway" might suggest the topics "robbery" and "crime"), affect-sensing (e.g. this email is sad and angry), analogy-making (e.g. "scissors," "razor," "nail clipper," and "sword" are perhaps like a "knife" because they are all "sharp," and can be used to "cut something"), and other contextoriented inferences. The knowledgebase is a semantic network presently consisting of over 1.6 million assertions of commonsense knowledge encompassing the spatial, physical, social, temporal, and psychological aspects of everyday life. Whereas similar large-scale semantic knowledgebases like Cyc and WordNet are carefully handcrafted, ConceptNet is generated automatically from the 700,000 sentences of the Open Mind Common Sense Project -- a World Wide Web based collaboration with over 14,000 authors.

We present statistical analyses of the large-scale structure of three types of semantic networks: word associations, WordNet, and Roget's thesaurus. We show that they have a small-world structure, characterized by sparse connectivity, short average path-lengths between words, and strong local clustering. In addition, the distributions of the number of connections follow power laws that indicate a scale-free pattern of connectivity, with most nodes having relatively few connections joined together through a small number of hubs with many connections. These regularities have also been found in certain other complex natural networks, such as the world wide web, but they are not consistent with many conventional models of semantic organization, based on inheritance hierarchies, arbitrarily structured networks, or high-dimensional vector spaces. We propose that these structures reflect the mechanisms by which semantic networks grow. We describe a simple model for semantic growth, in which each new word or concept is connected to an existing network by differentiating the connectivity pattern of an existing node. This model generates appropriate small-world statistics and power-law connectivity distributions, and also suggests one possible mechanistic basis for the effects of learning history variables (age-ofacquisition, usage frequency) on behavioral performance in semantic processing tasks.

A distributed attractor network is trained on an abstract version of the task of deriving the meanings of written words. When processing a word, the network starts from the final activity pattern of the previous word. Two words are semantically related if they overlap in their semantic features, whereas they are associatively related if one word follows the other frequently during training. After training, the network exhibits two empirical effects that have posed problems for distributed network theories: much stronger associative priming than semantic priming, and significant associative priming across an intervening unrelated item. It also reproduces the empirical findings of greater priming for low-frequency targets, degraded targets, and high-dominance category exemplars.

Structural priming in language production is a tendency to recreate a recently uttered syntactic structure in different words. This tendency can be seen independent of specific lexical items, thematic roles, or word sequences. Two alternative proposals about the mechanism behind structural priming include (a) short-term activation from a memory representation of a priming structure and (b) longer term adaptation within the cognitive mechanisms for creating sentences, as a form of procedural learning. Two experiments evaluated these hypotheses, focusing on the persistence of structural priming. Both experiments yielded priming that endured beyond adjacent sentences, persisting over 2 intervening sentences in Experiment 1 and over 10 in Experiment 2. Although memory may have short-term consequences for some components of this kind of priming, the persisting effects are more compatible with a learning account than a transient memory account. Speakers repeat themselves. Sometimes their repetitions are intentional, made for emphasis or other stylistic and social purposes (Giles & Powesland, 1975; Tannen, 1987), and sometimes they are accidental. They may involve almost

the properties of distributed network models, and support this account by demonstrating that an implemented simulation closely approximates the empirical findings despite the absence of expectancy-based processes and postlexical semantic matching. The results suggest that distributed network models can provide a viable single-mechanism account of lexical processing. Introduction It is well-established that people are faster and more accurate to read a word (e.g., BUTTER) when it is preceded by a related word (e.g., BREAD) compared with when it is preceded by an unrelated word (e.g., DOCTOR; The research was supported by an NIMH FIRST award (MH55628) to the first author and by NIMH Training Grant 5T32MH19102 and NICHD Grant 80258. The computational simulation was run using customized software written within the Xerion simulator (version 3.1) developed by Drew van Camp, Tony Plate, and Geoff Hinton at the Univers

In 7 experiments the authors investigated the locus of word frequency effects in speech production. Experiment 1 demonstrated a frequency effect in picture naming that was robust over repetitions. Experiments 2, 3, and 7 excluded contributions from object identification and initiation of articulation. Experiments 4 and 5 investigated whether the effect arises in accessing the syntactic word (lemma) by using a grammatical gender decision task. Although a frequency effect was found, it dissipated under repeated access to a word's gender. Experiment 6 tested whether the robust frequency effect arises in accessing the phonological form (lexeme) by having Ss translate words that produced homophones. Low-frequent homophones behaved like high-frequent controls, inheriting the accessing speed of their high-frequent homophone twins. Because homophones share the lexeme, not the lemma, this suggests a lexeme-level origin of the robust effect. The word frequency effect in speech production was discovered by Oldfield and Wingfield (1965). In a picture-naming task, they found that pictures with low-frequency (LF) names (such as syringe) took longer to name than pictures with high-frequency (HF) names (such as basket). Wingfield (1968)

The authors present a computational model that builds a holographic lexicon representing both word meaning and word order from unsupervised experience with natural language. The model uses simple convolution and superposition mechanisms (cf. B. B. Murdock, 1982) to learn distributed holographic representations for words. The structure of the resulting lexicon can account for empirical data from classic experiments studying semantic typicality, categorization, priming, and semantic constraint in sentence completions. Furthermore, order information can be retrieved from the holographic representations, allowing the model to account for limited word transitions without the need for built-in transition rules. The model demonstrates that a broad range of psychological data can be accounted for directly from the structure of lexical representations learned in this way, without the need for complexity to be built into either the processing mechanisms or the representations. The holographic representations are an appropriate knowledge representation to be used by higher order models of language comprehension, relieving the complexity required at the higher level.

concepts such as weather terms, proper names and emotional terms all segregate into their own meaning spaces. One advantage of representing meaning with vectors such as these is that, since each vector element is a symbol in the input stream (typically another word); all words have as their "features" other words. This translates into the ability to have a vector representation for abstract concepts as easily as one can have a representation for more basic concepts (Burgess & Lund, 1997b). This is important, if not absolutely crucial, when developing a memory model that purports to be general in nature. The other major aspect of categorization that the HAL model can address is the grammatical nature of word meaning. A clear categorization of nouns, prepositions, and Visual inspection of the MDS presentations in this paper all appear to show a robust separation of the various word groups. However, it is important to determine if these categorizations are clearly distinguished in the high-dimensional space. Our approach to this is to use an analysis of variance that compares the intragroup distances to the intergroup distances. This is accomplished by calculating all combinations of item-pair distances within a group and comparing them to all combinations of item-pair distances in the other groups. In all MDS presentations shown in this paper, these analyses were computed, and all differences discussed were reliable. verbs can be seen in Figure 2c. The generalizability of the HAL model to capture grammatical meaning as well as more traditional semantic characteristics of words is an important feature of the model (Burgess, 1998; Burgess & Lund, 1997a) and was part of our motivation to refer to the high-dimensional space as a context space rather than a semantic space. T...

The present research explored the nature of automatic associations formed between short-term motives (temptations) and the overriding goals with which they interfere. Five experimental studies, encompassing several self-regulatory domains, found that temptations tend to activate such higher priority goals, whereas the latter tend to inhibit the temptations. These activation patterns occurred outside of participants’ conscious awareness and did not appear to tax their mental resources. Moreover, they varied as a function of subjective goal importance and were more pronounced for successful versus unsuccessful self-regulators in a given domain. Finally, priming by temptation stimuli was found not only to influence the activation of overriding goals but also to affect goal-congruent behavioral choices. A delicious chocolate cake in the storefront of a bakery may remind individuals of the unfortunate fact that they should go on a diet. A thought of an exotic place, ideal for a relaxing vacation, may conjure up approaching deadlines at work. Momentarily alluring yet morally questionable activities may spontaneously bring to mind the image of a stern parent or a religious leader. On these and similar occasions, elaborating on a seemingly desirable course

xi 1 Introduction 1 1.1 Intuitions and Evidence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.2 Previous Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.1 The Classical Dual Route Model . . . . . . . . . . . . . . . . . . . . . . . 6 1.2.2 Seidenberg and McClelland 1989 . . . . . . . . . . . . . . . . . . . . . . 10 1.2.3 Plaut and Shallice 1993 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.2.4 Plaut et al. 1996: Naming . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.2.5 Bullinaria 1996 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 1.2.6 Plaut 1997: Lexical Decision . . . . . . . . . . . . . . . . . . . . . . . . . 15 1.2.7 Harm and Seidenberg 1998: Naming . . . . . . . . . . . . . . . . . . . . 16 1.3 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2 A New Computational Model 18 2.1 Principles . . . . . . . . . . . . . . . . . . . . . . . . ...