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

We develop a new computational model for representing the fine-grained meanings of near-synonyms and the differences between them. We also develop a sophisticated lexical-choice process that can decide which of several near-synonyms is most appropriate in a particular situation. This research has direct applications in machine translation and text generation. We first identify the problems of representing near-synonyms in a computational lexicon and show that no previous model adequately accounts for near-synonymy. We then propose a preliminary theory to account for near-synonymy, relying crucially on the notion of granularity of representation, in which the meaning of a word arises out of a context-dependent combination of a context-independent core meaning and a set of explicit differences to its near-synonyms. That is, near-synonyms cluster together. We then develop a clustered model of lexical knowledge, derived from the conventional ontological model. The model cuts off the ontology at a coarse grain, thus avoiding an awkward proliferation of language-dependent concepts in the ontology, and groups near-synonyms into subconceptual clusters that are linked to the ontology. A cluster differentiates near-synonyms in terms of fine-grained aspects of denotation, implication, expressed attitude, and style. The model is general enough to account for other types of variation, for instance, in collocational behaviour. An efficient, robust, and flexible fine-grained lexical-choice process is a consequence of a clustered model of lexical knowledge. To make it work, we formalize criteria for lexical choice as preferences to express certain concepts with varying indirectness, to express attitudes, and to establish certain styles. The lexical-choice process itself works on two tiers: between clusters and between near-synonyns of clusters. We describe our prototype implementation of the system, called I-Saurus.

Natural language is the most used representation for stating requirements on computer-based systems in industry. However, natural language is inherently ambiguous. Customers and software developers can disagree on the interpretation of a requirement without being aware of this fact. This disagreement can result in disastrous software failures. We argue that ambiguity is a more complex phenomenon than is often recognized in the literature. While inconsistencies and some types of incompleteness can be mechanically detected in formal specifications, ambiguities in informal specifications often result in incorrect formal specifications. These misinterpretations can be detected only by execution or inspection of the formal specification. We suggest an inspection technique for detecting ambiguities in informal requirement documents before formal specifications are produced in order to avoid misinterpretations, rather than searching for them afterwards. We show how this technique can be tailored to different project contexts with the help of metamodels to increase its effectiveness. Finally, we report on experimental validation of the technique. 1

A continuum between purely isolated and purely interrelated concepts is described. A concept is interrelated to the extent that it is influenced by other concepts. Methods for manipulating and identiying a concept's degree of interrelatedness are introduced. Relatively isolated concepts are empirically identified by a relatively large use of nondiagnostic features, and by better categorization performance for a concept's prototype than for a caricature of the concept. Relatively interrelated concepts are identified by minimal use of nondiagnostic features, and by better categorization performance for a caricature than a prototype. A concept is likely to be relatively isolated when: subjects are instructed to create images for their concepts rather than find discriminating features, concepts are given unrelated labels, and the categories that are displayed alternate rarely between trials. The entire set of manipulations and measurements supports a graded distinction between isolated and interrelated concepts. The distinction is applied to current models of category learning, and a connectionist framework for interpreting the empirical results is presented. Modern research on concept representation and learning has evolved from two traditions. One tradition connects concept acquisition with language in general and word learning in specific (Lakoff, 1986; Saussure, 1915/1959). Concepts are approximately equated with single words or phrases. In this tradition, for example, evidence that a child has acquired the adult concept of dog comes from the child's use of the word "dog" to designate dogs. The other tradition connects concept acquisition with object recognition (Biederman, 1987). From this perspective, concept learning involves learning to correctly cate...

. This work belongs to a family of research efforts, called microtheories and aimed at describing the static meaning of all lexical categories in several languages in the framework of the MikroKosmos project on computational semantics. The latter also involves other static microtheories describing world knowledge and syntax-semantics mapping as well as dynamic microtheories connected with the actual process of text analysis. This paper describes our approach to determining and representing adjectival meaning, compares it with the body of knowledge on adjectives in literature and presents a detailed, practically tested methodology and heuristics for the acquisition of lexical entries for adjectives. The work was based on the set of over 6,000 English and about 1,500 Spanish adjectives obtained from task-oriented corpora. Introduction The topic of this paper is the information about adjectival meaning which should be included in a computational lexicon. Thus, we concentrate on...

There have been several reports in the literature of faster visual lexical decisions to words that are semantically ambiguous. All current models of this ambiguity advantage assume that it is the presence of multiple unrelated meanings that produce this benefit. A set of three lexical decision experiments reported here challenge this assumption. We contrast the ambiguity seen in words like bark, which have multiple unrelated meanings, with words that have multiple related word senses (e.g., twist). In all three experiments we find that while multiple word senses do produce faster responses, ambiguity between multiple meanings delays recognition. These results suggest that, while competition between the multiple meanings of ambiguous words delays their recognition, the rich semantic representations associated with words with many senses facilitate their recognition. © 2002 Elsevier Science (USA) Key Words: lexical ambiguity; polysemy; distributed semantic representations. Many words are semantically ambiguous, and can refer to more than one concept. For example, bark can refer either to a part of a tree or to the sound made by a dog. To understand such words, we must select one of these different interpretations, normally on the basis of the context

Natural Language Processing (NLP) systems usually require large amounts of pre-coded domain knowledge to perform semantic analysis automatically. Until repositories of such background knowledge are widely available, these systems may not scale up to non-trivial applications of NLP. This paper describes the design and implementation of a system that uses surface-syntactic information to interpret interactively semantic relationships between clauses. English technical texts are analyzed by a domain-independent parser that produces detailed parse trees of the input. The system then examines clausal connectives and syntactic verb phrase features to determine what kinds of semantic relationships exist between clauses. The results of this activity are used in a large Knowledge Acquisition system that, by design, requires little a priori semantic knowledge. We present a set of semantic labels appropriate to syntactically connected clauses (Clause-Level Relationships) and a description of the...

This handbook is about writing software requirements specifications and legal contracts, two kinds of documents with similar needs for completeness, consistency, and precision. Particularly when these are written, as they usually are, in natural language, ambiguity---by any definition---is a major cause of their not specifying what they should. Simple misuse of the language in which the document is written is one source of these ambiguities.

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.

The modern computational lexical semantics reached a point in its development when it has become necessary to define the premises and goals of each of its several trends. This paper proposes ten choices in terms of which these premises and goals can be discussed. It is argued that the central questions include the use of lexical rules for generating word senses; the role of syntax, pragmatics, and formal semantics in the specification of lexical meaning; the use of a world model, or ontology, as the organizing principle for lexical-semantic descriptions; the use of rules with limited scope; the relation between static and dynamic resources; the commitment to descriptive coverage; the trade-off between generalization and idiosyncracy; and, finally, the adherence to the "supply-side" (method-oriented) or "demand-side" (task-oriented) ideology of research. The discussion is inspired by, but not limited to, the comparison between the generative lexicon approach and the ontologi...