"Its publication should be a major event for cognitive linguistics and should pose a major challenge for cognitive science. In addition, it should have repercussions in a variety of disciplines, ranging from anthropology and psychology to epistemology and the philosophy of science.... Lakoff asks: What do categories of language and thought reveal about the human mind? Offering both general theory and minute details, Lakoff shows that categories reveal a great deal."—David E. Leary, American Scientist.

This paper presents a new method for producing a dictionary of subcategorization frames from unlabelled text corpora. It is shown that statistical filtering of the results of a finite state parser running on the output of a stochastic tagger produces high quality results, despite the error rates of the tagger and the parser. Further, it is argued that this method can be used to learn all subcategorization frames, whereas previous methods are not extensible to a general solution to the problem.

The book can also be used as an excellent text for graduate-level courses in AI, operations research, or applied probability.

This work is an investigation into part of the human sentence parsing mechanism (HSPM). The major test of the psychological validity of any model of the HSPM is that it fail on precisely those sentences that humans find to be garden paths. It is hypothesized that the HSPM consists of at least two processes. We call the first process the syntactic processor, and the second will be known as the semantic processor.It is hypothesized that the syntactic processor is unconscious, deterministic (...) and fast, but limited. While most ambiguities are resolved on the basis of syntactic information, when the syntactic processor can no longer guarantee a correct analysis, semantic information is used to help resolve the ambiguity. This model leads to a better prediction and explanation of which sentences will cause people to garden path. (shrink)

Much of the progress in the fields constituting cognitive science has been based upon the use of explicit information processing models, almost exclusively patterned after conventional serial computers. An extension of these ideas to massively parallel, connectionist models appears to offer a number of advantages. After a preliminary discussion, this paper introduces a general connectionist model and considers how it might be used in cognitive science. Among the issues addressed are: stability and noise‐sensitivity, distributed decision‐making, time and sequence problems, and (...) the representation of complex concepts. (shrink)

In this particularly well written volume Graeme Hirst presents a theoretically motivated foundation for semantic interpretation (conceptual analysis) by computer, and shows how this framework facilitates the resolution of both lexical and syntactic ambiguities.

We present a processing model that integrates same important psychological claims about the human sentence‐parsing mechanism: namely, that processing is influenced by limitations an working memory and by various syntactic preferences. The model uses time‐constraint information to resolve conflicting preferences in a psychologically plausible way. The starting paint far this proposal is the Sausage Machine model (Fodor & Frazier, 1980: Frazier & Fodor, 1978). From there, we attempt to overcome the original model's dependence an ad hoc aspects of its grammar, (...) and its omission of verb‐frame preferences. We also add mechanisms far lexical disambiguation and semantic processing in parallel with syntactic processing. (shrink)

Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency – as though these inferences were a reflexive response of their cognitive apparatus. Furthermore, these inferences are drawn with reference to a large body of background knowledge. This remarkable human ability seems paradoxical given the complexity of reasoning reported by researchers in artificial intelligence. It also poses a challenge for cognitive science and computational neuroscience: How can a system of simple and slow neuronlike elements represent a large (...) body of systemic knowledge and perform a range of inferences with such speed? We describe a computational model that takes a step toward addressing the cognitive science challenge and resolving the artificial intelligence paradox. We show how a connectionist network can encode millions of facts and rules involving n-ary predicates and variables and perform a class of inferences in a few hundred milliseconds. Efficient reasoning requires the rapid representation and propagation of dynamic bindings. Our model (which we refer to as SHRUTI) achieves this by representing (1) dynamic bindings as the synchronous firing of appropriate nodes, (2) rules as interconnection patterns that direct the propagation of rhythmic activity, and (3) long-term facts as temporal pattern-matching subnetworks. The model is consistent with recent neurophysiological evidence that synchronous activity occurs in the brain and may play a representational role in neural information processing. The model also makes specific psychologically significant predictions about the nature of reflexive reasoning. It identifies constraints on the form of rules that may participate in such reasoning and relates the capacity of the working memory underlying reflexive reasoning to biological parameters such as the lowest frequency at which nodes can sustain synchronous oscillations and the coarseness of synchronization. (shrink)