this paper, I will discuss four major topics relating to current research in lexical semantics: methodology, descriptive coverage, adequacy of the representation, and the computational usefulness of representations. In addressing these issues, I will discuss what I think are some of the central problems facing the lexical semantics community, and suggest ways of best approaching these issues. Then, I will provide a method for the decomposition of lexical categories and outline a theory of lexical semantics embodying a notion of cocompositionality and type coercion, as well as several levels of semantic description, where the semantic load is spread more evenly throughout the lexicon. I argue that lexical decomposition is possible if it is performed generatively. Rather than assuming a fixed set of primitives, I will assume a fixed number of generative devices that can be seen as constructing semantic expressions. I develop a theory of Qualia Structure, a representation language for lexical items, which renders much lexical ambiguity in the lexicon unnecessary, while still explaining the systematic polysemy that words carry. Finally, I discuss how individual lexical structures can be integrated into the larger lexical knowledge base through a theory of lexical inheritance. This provides us with the necessary principles of global organization for the lexicon, enabling us to fully integrate our natural language lexicon into a conceptual whole

This paper presents context-group discrimination, a disambiguation algorithm based on clustering. Senses are interpreted as groups (or clusters) of similar contexts of the ambiguous word. Words, contexts, and senses are represented in Word Space, a high-dimensional, real-valued space in which closeness corresponds to semantic similarity. Similarity in Word Space is based on second-order co-occurrence: two tokens (or contexts) of the ambiguous word are assigned to the same sense cluster if the words they co-occur with in turn occur with similar words in a training corpus. The algorithm is automatic and unsupervised in both training and application: senses are induced from a corpus without labeled training insta,nces or other external knowledge sources. The paper demonstrates good performance of context-group discrimination for a sample of natural and artificial ambiguous words

This paper describes a program that disambiguates English word senses in unrestricted text using statistical models of the major Roget's Thesaurus categories. Roget's categories serve as approximations of conceptual classes. The categories listed for a word in Roget's index tend to correspond to sense distinctions; thus selecting the most likely category provides a useful level of sense disambiguation. The selection of categories is accomplished by identifying and weighting words that are indicative of each category when seen in context, using a Bayesian theoretical framework. Other

In this paper, we present a new approach for word sense disambiguation (WSD) using an exemplar-based learning algorithm. This approach

this paper, we examine the idea of lexical chains as such a representation. We show how they can be constructed by means of WordNet, and how they can be applied in one particular linguistic task: the detection and correction of malapropisms.

Introduction An impressive array of statistical methods have been developed for word sense identification. They range from dictionary-based approaches that rely on definitions (Vronis and Ide 1990; Wilks et al. 1993) to corpus-based approaches that use only word cooccurrence frequencies extracted from large textual corpora (Schfitze 1995; Dagan and Itai 1994). We have drawn on these two traditions, using corpus-based co-occurrence and the lexical knowledge base that is embodied in the WordNet lexicon. The two traditions complement each other. Corpus-based approaches have the advantage of being generally applicable to new texts, domains, and corpora without needing costly and perhaps error-prone parsing or semantic analysis. They require only training corpora in which the sense distinctions have been marked, but therein lies their weakness. Obtaining training materials for statistical methods is costly and timeconsuming --it is a "knowledge acquisition bottleneck" (Gale, Church, and Y

The problems of access -- retrieving linguistic structure from some mental grammar -- and disambiguation -- choosing among these structures to correctly parse ambiguous linguistic input -- are fundamental to language understanding. The literature abounds with psychological results on lexical access, the access of idioms, syntactic rule access, parsing preferences, syntactic disambiguation, and the processing of garden-path sentences. Unfortunately, it has been difficult to combine models which account for these results to build a general, uniform model of access and disambiguation at the lexical, idiomatic, and syntactic levels. For example psycholinguistic theories of lexical access and idiom access and parsing theories of syntactic rule access have almost no commonality in methodology or coverage of psycholinguistic data. This paper presents a single probabilistic algorithm which models both the access and disambiguation of linguistic knowledge. The algorithm is based on a parallel parser which ranks constructions for access, and interpretations for disambiguation, by their conditional probability. Low-ranked constructions and interpretations are pruned through beam-search; this pruning accounts, among other things, for the garden-path effect. I show that this motivated probabilistic treatment accounts for a wide variety of psycholinguistic results, arguing for a more uniform representation of linguistic knowledge and for the use of probabilisticallyenriched grammars and interpreters as models of human knowledge of and processing of language.

This paper addresses the problem of how to identify the intended meaning of individual words in unrestricted texts, without necessarily having access to complete representations of sentences. To discriminate senses, an understander can consider a diversity of information, including syntactic tags, word frequencies, collocations, semantic context, role-related expectations, and syntactic restrictions. However, current approaches make use of only small subsets of this information. Here we will describe how to use the whole range of information. Our discussion will include how the preference cues relate to general lexical and conceptual knowledge and to more specialized knowledge of collocations and contexts. We will describe a method of combining cues on the basis of their individual specificity, rather than a fixed ranking among cue-types. We will also discuss an application of the approach in a system that computes sense tags for arbitrary texts, even when it is unable to determine a single syntactic or semantic representation for some sentences.

This paper describes an accurate, relatively inexpensive method for the disambiguation of noun homographs using large text corpora. The algorithm checks the context surrounding the target noun against that of previously observed instances and chooses the sense for which the most evidence is found, where evidence consists of a set of orthographic, syntactic, and lexical features. Because the sense distinctions made are coarse, the disambiguation can be accomplished without the expense of knowledge bases or inference mechanisms. An implementation of the algorithm is described which, starting with a small set of hand-labeled instances, improves its results automatically via unsupervised training. The approach is compared to other attempts at homograph disambiguation using both machine readable dictionaries and unrestricted text and the use of training instances is determined to be a crucial difference. 1 Introduction Large text corpora and the computational resources to handle them have ...

Word sense disambiguation has been recognized as a major problem in natural language processing research for over forty years. Much of this work has been stymied by difficulties in acquiring appropriate lexical resources, such as semantic networks and annotated corpora. Following the suggestion in Brown et al. (1991a) and Dagan et al. (1991), we have achieved considerable progress recently by taking advantage of a new source of testing and training materials. Rather than depending on small amounts of hand-labeled text, we have been making use of relatively large amounts of parallel text, text such as the Canadian Hansards (parliamentary debates), which are available in two (or more) languages. The translation can often be used in lieu of hand-labeling. For example, consider the polysemous word sentence, which has two major senses: (1) a judicial sentence, and (2), a syntactic sentence. We can collect a number of sense (1) examples by extracting instances that are translated as peine, and we can collect a number of sense (2) examples by extracting instances that are translated as phrase. In this way, we have been able to acquire a considerable amount of testing and training material for developing and testing our disambiguation algorithms. The availability of this testing and training material has enabled us to develop quantitative disambiguation methods that achieve 90 % accuracy in discriminating between two very distinct senses of a noun such as