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.

Morphology by an Attractor Network. This paper investigates the ability of a connectionist attractor network to learn a system analogous to part of the system of English verbal morphology. The model learned to produce phonological representations of stems and inflected forms in response to semantic inputs. The model was able to resolve several outstanding problems. It displayed all three stages of the characteristic U-shaped pattern of acquisition of the English past tense (early correct performance, a period of overgeneralizations and other errors, and eventual mastery). The network is also able to simulate direct access (the ability to create an inflected form directly from a semantic representation without having to ftrSt access an intermediate base form). The model was easily able to resolve homophonic verbs (such as ring and wring). In addition, the network was able to apply the past tense, third person-8 and progressive ing suffixes productively to novel forms and to display sensitivity to the subregularities that mark families of irregular past tense forms. The network also simulates the frequency by regularity interaction that has been found in reaction time studies of human subjects and provides a possible explanation for some hypothesized universal constraints upon morphological operations.

This thesis describes HABLAR, a computational model of the sensorimotor foundations of early childhood phonological development. HABLAR (an acronym for "Hierarchical Articulatory Based Language Acquisition by Reinforcement learning" and Spanish for "to speak") is intended to replicate the major milestones of emerging speech and demonstrate key characteristics of normal development, including the phonetic characteristics of babble, systematic and context-sensitive patterns of sound substitutions and deletions, overgeneralization errors, and the emergence of adult phonemic organization. It should also mimic abnormal phonological development under certain conditions of damage or degradation. HABLAR simulates a complete sensorimotor system consisting of an auditory system that detects and categorizes speech sounds using only acoustic cues drawn from its linguistic environment, an articulatory system that generates synthetic speech based on a realistic computer model of the vocal tract, an...

This thesis describes a computational model of child language acquisition which acquires a recursive phrase-structure grammar in the absence of X-Bar Theory. The model assumes no grammar, lexicon, or segmentation. Input utterances include phrases as well as sentences, of no more than two levels of embedding, paired with their semantic representations. The initial products of acquisition are a lexicon of unanalysed utterances and a finite-state grammar. The lexical items acquired guide further lexical acquisition, which results in their segmentation, and thus triggers the acquisition of a phrase-structure grammar. The Lexical-Functional Grammar formalism is used, so that acquiring C-Structure, or phrase structure, can be viewed as mapping the ordered utterance onto the unordered F-Structure, a shallow semantic representation. Generalization over the phrase-structure rules acquired results in the induction of syntactic categories, and it is this which gives rise to recursion in the gramm...

We present a new model of language learning which is based on the following idea: if a language learner does not know which phrase-structure trees should be assigned to initial sentences, s/he allows (implicitly) for all possible trees and lets linguistic experience decide which is the ‘best’ tree for each sentence. The best tree is obtained by maximizing ‘structural analogy ’ between a sentence and previous sentences, which is formalized by the most probable shortest combination of subtrees from all trees of previous sentences. Corpus-based experiments with this model on the Penn Treebank and the Childes database indicate that it can learn both exemplar-based and rulebased aspects of language, ranging from phrasal verbs to auxiliary fronting. By having learned the syntactic structures of sentences, we have also learned the grammar implicit in these structures, which can in turn be used to produce new sentences. We show that our model mimicks children’s language development from item-based constructions to abstract constructions, and that the model can simulate some of the errors made by children in producing complex questions. 1 1

Learning the English past tense is characterized by a U-shaped learning function for the irregular verbs. Existing cognitive models rely on a sudden increases in vocabulary, a high token-frequency of regular verbs, and convoluted schemes of feedback in order to model this phenomenon. All these assumptions are at odds with empirical data. In this paper a hybrid ACT-R model is presented that shows U-shaped learning without direct feedback, changes in vocabulary, or unrealistically high rates of regular verbs. The model is capable of learning the default rule, even if regular forms are infrequent. It can also help explore the question of why there is a distinction between regular and irregular verbs in the first place, by examining the costs and benefits of both types of verbs.

All rights of reproduction in any form reserved.

www.elsevier.com/locate/cognit Why do children learn to say “Broke”? A model of learning the past tense without feedback

How do children cope with the general regularities that govern language while keeping track of the exceptions to them? This question has been the subject of debate for many years and it is still an open question. In particular, learning the English past tense has been studied in depth given that it is a simple problem that combines a rulelike process with many irregularities. In this paper we try to extend these studies to a quite more complex problem: the Spanish verb inflectional system. This paper presents an ACT-R model that shows the well-known U-shaped learning and mimics in many aspects the process of learning exhibited by children. Thus, our approach shows how a highly inflected morphology system can be acquired in terms of dual-mechanism theories and sheds light on the posible structures involved in general language acquisition.

The effects of frequency and neighbourhood density on adult speakers ’ productivity with Polish case inflections: An empirical test of usage-based approaches to morphology