Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves: (...) the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands: indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly context‐dependent, while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction. (shrink)

The vast expressive power of language is made possible by two principles: the arbitrary soundmeaning pairing underlying words, and the discrete combinatorial system underlying grammar. These principles implicate distinct cognitive mechanisms: associative memory and symbolmanipulating rules. The distinction may be seen in the difference between regular inflection (e.g., walk-walked), which is productive and open-ended and hence implicates a rule, and irregular inflection (e.g., come-came, which is idiosyncratic and closed and hence implicates individually memorized words. Nonetheless, two very different theories have (...) attempted to collapse the distinction; generative phonology invokes minor rules to generate irregular as well as regular forms, and connectionism invokes a pattern associator memory to store and retrieve regular as well as irregular forms. I present evidence from three disciplines that supports the traditional word/rule distinction, though with an enriched conception of lexical memory with some of the properties of a pattern-associator. Rules, nonetheless, are distinct from patternassociation, because a rule concatenates a suffix to a symbol for verbs, so it does not require access to memorized verbs or their sound patterns, but applies as the "default," whenever memory access fails. I present a dozen such circumstances, including novel, unusual-sounding, and rootless and headless derived words, in which people inflect the words regularly (explaining quirks like flied out, low-lifes, and Walkmans). A comparison of English to other languages shows that contrary to the connectionist account, default suffixation is not due to numerous regular words reinforcing a pattern in associative memory, but to a memory-independent, symbol-concatenating mental operation. (shrink)

Language acquisition may be one of the most difficult tasks that children face during development. They have to segment words from fluent speech, figure out the meanings of these words, and discover the syntactic constraints for joining them together into meaningful sentences. Over the past couple of decades, computational modeling has emerged as a new paradigm for gaining insights into the mechanisms by which children may accomplish these feats. Unfortunately, many of these models assume a computational complexity and linguistic knowledge (...) likely to be beyond the abilities of developing young children. This article shows that, using simple statistical procedures, significant correlations exist between the beginnings and endings of a word and its lexical category in English, Dutch, French, and Japanese. Therefore, phonetic information can contribute to individuating higher level structural properties of these languages. This article also presents a simple 2‐layer connectionist model that, once trained with an initial small sample of words labeled for lexical category, can infer the lexical category of a large proportion of novel words using only word‐edge phonological information, namely the first and last phoneme of a word. The results suggest that simple procedures combined with phonetic information perceptually available to children provide solid scaffolding for emerging lexical categories in language development. (shrink)

Words associated with perceptually salient, highly imageable concepts are learned earlier in life, more accurately recalled, and more rapidly named than abstract words (R. W. Brown, 1976; Walker & Hulme, 1999). Theories accounting for this concreteness effect have focused exclusively on semantic properties of word referents. A novel possibility is that word structure may also contribute to the effect. We report a corpus-based analysis of the phonological and morphological structures of a large set of nouns with imageability ratings (N = (...) 2,023). High- and low-imageability nouns differed by length, etymology, prosody, affixation, phonological neighborhood density, and rates of consonant clustering. On average, nouns denoting abstract concepts were longer, more derivationally complex, and emerged in English from a different distribution of languages than did concrete nouns. We address implications for interactivity of word form and meaning as pertain to theories of word concreteness, lexical acquisition, and word processing. (shrink)

It is a reasonable assumption that universal properties of natural languages are not accidental. They occur either because they are underwritten by genetic code, because they assist in language processing or language learning, or due to some combination of the two. In this paper we investigate one such language universal: the suffixing preference across the world’s languages, whereby inflections tend to be added to the end of words. A corpus analysis of child‐directed speech in English found that suffixes were more (...) accurate at cuing the grammatical category of the root word than were prefixes. An artificial language experiment found that there was a learning advantage for suffixes over prefixes in terms of grammatical categorization within an artificial language. The results are consistent with an account of language universals that originate in general purpose learning mechanisms. (shrink)

Abstract Since their inception, distributional models of semantics have been criticized as inadequate cognitive theories of human semantic learning and representation. A principal challenge is that the representations derived by distributional models are purely symbolic and are not grounded in perception and action; this challenge has led many to favor feature-based models of semantic representation. We argue that the amount of perceptual and other semantic information that can be learned from purely distributional statistics has been underappreciated. We compare the representations (...) of three feature-based and nine distributional models using a semantic clustering task. Several distributional models demonstrated semantic clustering comparable with clustering-based on feature-based representations. Furthermore, when trained on child-directed speech, the same distributional models perform as well as sensorimotor-based feature representations of children’s lexical semantic knowledge. These results suggest that, to a large extent, information relevant for extracting semantic categories is redundantly coded in perceptual and linguistic experience. Detailed analyses of the semantic clusters of the feature-based and distributional models also reveal that the models make use of complementary cues to semantic organization from the two data streams. Rather than conceptualizing feature-based and distributional models as competing theories, we argue that future focus should be on understanding the cognitive mechanisms humans use to integrate the two sources. (shrink)