Selectional constraints are limitations on the applicability of predicates to arguments. For example, the statement “The number two is blue” may be syntactically well formed, but at some level it is anomalous — BLUE is not a predicate that can be applied to numbers. According to the influential theory of (Katz and Fodor, 1964), a predicate associates a set of defining features with each argument, expressed within a restricted semantic vocabulary. Despite the persistence of this theory, however, there is widespread agreement about its empirical shortcomings (McCawley, 1968; Fodor, 1977). As an alternative, some critics of the Katz-Fodor theory (e.g. (Johnson-Laird, 1983)) have abandoned the treatment of selectional constraints as semantic, instead treating them as indistinguishable from inferences made on the basis of factual knowledge. This provides a better match for the empirical phenomena, but it opens up a different problem: if selectional constraints are the same as inferences in general, then accounting for them will require a much more complete understanding of knowledge representation and inference than we have at present. The problem, then, is this: how can a theory of selectional constraints be elaborated without first having either an empirically adequate theory of defining features or a comprehensive theory of inference? In this dissertation, I suggest that an answer to this question lies in the representation of conceptual

Abstract not found

The automatic disambiguation of word senses has been an interest and concern since the earliest days of computer treatment of language in the 1950's. Sense disambiguation is an “intermediate task ” (Wilks and Stevenson, 1996) which is not an end in itself, but rather is necessary at one level or another to accomplish most natural language processing tasks. It is

In this paper, we describe a means for automatically building very large neural networks (VLNNs) from definition texts in machine-readable dictionaries, and demonstrato the use of these networks for word sense disambiguation. Our method brings together two earlier, independent approaches to word sense disambiguation: the use of machine-readable dictionaries and spreading and activation models. The automatic construction of VLNNs enables real-size experiments with neural networks for natural languageprocessing, which in turn provides insight into their behavior and design and can lead to possible improvements.

Machine-readable versions of everyday dictionaries have been seen as a likely source of information for use in natural language processing because they contain an enormous amount of lexical and semantic knowledge. However, after 15 years of research, the results appear to be disappointing. No comprehensive evaluation of machine-readable dictionaries (MRDs) as a knowledge source has been made to date, although this is necessary to determine what, if anything, can be gained from MRD research. To this end, this paper will first consider the postulates upon which MRD research has been based over the past fifteen years, discuss the validity of these postulates, and evaluate the results of this work. We will then propose possible future directions and applications that may exploit these years of effort, in the light of current directions in not only NLP research, but also fields such as lexicography and electronic publishing.

In this paper we show that previously applied data models are inadequate for lexical databases. In particular, we show that relational data models, including unnormalized models which allow the nesting of relations, cannot fully capture the structural properties of lexical information. We propose an alternative feature-based model which allows for a full representation of sense nesting and defines a factoring mechanism that enables the elimination of redundant information. We then demonstrate that feature structures map readily to an object-oriented data model and show how our model can be implemented in an object-oriented DBMS.

In this paper we apply a spreading activation algorithm to the problem of mapping senses between machine readable dictionaries, which is required in order to combined information extracted from them. The algorithm is run over networks automatically constructed from dictionary definition texts. On a sample corpus of sense definitions, our strategy correctly identifies the corresponding homograph in a second dictionary in 97% of the cases, and the correct sense within that homograph in 90% of the cases. This result is a substantial improvement over previously proposed strategies, such as Lesk's method. It also demonstrates that spreading activation strategies, which have rarely been used in computational lexicography, are one means to exploit the full potential of relations implicitly encoded in machine-readable dictionaries. The authors would like to thank Lisa Lassek for her contribution to the work of this project. 2 1. Introduction It is widely recognized that machine re...

this paper, we report the results of a quantitative evaluation of automatically extracted semantic data. Our results show that for any one dictionary, 55-70% of the extracted information is garbled in some way. These results at first call into doubt the validity of automatic extraction from dictionaries. However, in section 4 we show that these results can be dramatically reduced to about 6% by several means--most significantly, by combining the information extracted from five dictionaries. It therefore appears that even if individual dictionaries are an unreliable source of semantic information, multiple dictionaries can play an important role in building large lexical-semantic databases.

This paper is a survey of the current machine translation research in the US, Europe and Japan. A short history of machine translation is presented first, followed by an overview of the current research work. Representative examples of a wide range of different approaches adopted by machine translation researchers are presented. These are described in detail along with a discussion of the practicalities of scaling up these approaches for operational environments. In support of this discussion, issues in, and techniques for, evaluating machine translation systems are addressed.

Machine-readable versions of everyday dictionaries have been seen as a likely source of information for use in natural language processing because they contain an enormous amount of lexical and semantic knowledge. However, after 15 years of research, the results appear to be disappointing. No comprehensive evaluation of machine-readable dictionaries (MRDs) as a knowledge source has been made to date, although this is necessary to determine what, if anything, can be gained from MRD research. To this end, this paper will first consider the postulates upon which MRD research has been based over the past fifteen years, discuss the validity of these postulates, and evaluate the results of this work. We will then propose possible future directions and applications that may exploit these years of effort, in the light of current directions in not only NLP research, but also fields such as lexicography and electronic publishing.