Naturally occurring speech contains only a limited amount of complex recursive structure, and this is reflected in the empirically documented difficulties that people experience when processing such structures. We present a connectionist model of human performance in processing recursive language structures. The model is trained on simple artificial languages. We find that the qualitative performance profile of the model matches human behavior, both on the relative difficulty of center-embedded and cross-dependency, and between the processing of these complex recursive structures and right-branching recursive constructions. We analyze how these differences in performance are reflected in the internal representations of the model by performing discriminant analyses on these representation both before and after training. Furthermore, we show how a network trained to process recursive structures can also generate such structures in a probabilistic fashion. This work suggests a novel expla...

Many theories have been proposed to explain difficulty with center embedded constructions, most attributing the problem to some kind of limited capacity short-term memory. However, these theories have developed for the most part independently of more traditional memory research, which has focused on uncovering general principles such as chunking and interference. This article attempts to gain some unification with this research by suggesting that an interesting range of core sentence processing phenomena can be explained as interference effects in a sharply limited syntactic working memory. These include difficult and acceptable embeddings, as well as certain limitations on ambiguity resolution, length effects in garden path structures, and the requirement for locality in syntactic structure. The theory takes the form of an architecture for parsing which can index no more than two constituents under the same syntactic relation. A limitation of two or three items shows up in a variety o...

Abstract not found

Abstract not found

ing away from irrelevant details is a theoretical virtue, but the kinds of abstractions that module geography makes can lead to incorrect inferences from data. That such a possibility exists is clearly demonstrated by the working memory research of Just & Carpenter (1992). Briefly, Just and Carpenter have argued that some garden path effects that were previously interpreted in terms of a syntactically encapsulated module can instead be explained by individual differences in working memory capacity. Such an explanation is not considered in a theoretical framework that systematically ignores the role of memory structures in parsing. This point should be taken regardless of whether one is convinced by the current body of empirical support for this particular model---the fact remains that such an explanation could in principle account for the data, and these alternative explanations are only discovered by developing functionally complete architectures. The next few sections describes what ...

This discussion outlines and implements the theory of an inductive inference technique that automatically discovers classes among large numbers of input patterns, generates operational definitions of class membership with explicit levels of confidence, creates a continuously updated "self-organized" coded hierarchical taxonomic classification of patterns, and recognizes to which already discovered class or classes, if any, a new input belongs in an information-theoretically efficient way. Relationships to the "scientific method" and learning are discussed.

which is/are unaval able. 12-1-84 CENTER FOR THE STUDY OF READING Technical Report No. 43

A computer program is described which will assign each word in an English text to its form class or part of speech. The program operates at relatively high speed in only a limited storage space. About half of the word-events in a corpus are identified through the use of a small dictionary of function words and frequently occurring lexical words. Some suffix tests and Iogical-decislon rules are employed to code additional words. Finally, the remaining words are assigned to one class or another on the basis of the most probable form classes to occur within the already identified contexts. The conditional probabilities used as a basis for this coding were empirically derived from a separate hand-coded corpus. On preliminary trials, the accuracy of the coder was 91 % to 93%, with obvious ways of improving the algorithm being suggested by an analysis of the results. I.

This thesis develops a cognitive linguistic approach to language comprehension. The cognitive approach differs from traditional linguistic approaches in that linguistic description is seen as an integral part of the description of cognition, and that the object of description is the nature of conceptual structures, the processes which relate these conceptual structures, and the effect of context upon these processes. As a cognitive description within cognitive science, a computational approach is adopted: language comprehension is described in terms of two modules, a linguistic processing module and a discourse processing module. Within these modules, conceptual structures and processes are given a uniform characterization: structures are characterized as partial objects which are extended by processes into (potentially) less partial objects. In the linguistic processing module, linguistic expressions are characterized as signs which combine as head and modifier. The conceptual structu...

This article examines cognitive process models of human sentence comprehension based on the idea of informed search. These models are rational in the sense that they strive to quickly find a good syntactic analysis. Informed search derives a new account of garden pathing that handles traditional counterexamples. It supports a symbolic explanation for local coherence as well as an algorithmic account of entropy reduction. The models are expressed in a broad framework for theories of human sentence comprehension. 1