We introduce two abstraction mechanisms for streamlining the process of semantic interpretation. Configurational descriptions of dependency graphs increase the linguistic generality of interpretation schemata, while interfacing them to lexical and conceptual inheritance hierarchies reduces the amount and complexity of semantic specifications.

1. Introduction The question of polysemy and the representation of different lexical word-senses has recently attracted an increased interest in the linguistics and computational linguistics literature. has proposed to enrich the format of lexical representation so that a number of 'novel' word senses can be generated. In this paper, we discuss GLT and show that, while being able to derive nove...

Five phenomena concerning the meanings of words are outlined in this paper. They concern (1) our limited introspective access to the nature of lexical representations; (2) the existence of lexical entries that make accessible the sense of a word; (3) the effects of context on the interpretation of words; (4) the systematic gaps in the acquisition of lexical knowledge; and (5) the existence of d...

Terminology is the surface appearance of relevant domain concepts. Though many methods have been presented to extract from texts relevant domain terminology, a semantic interpretation of these terms is still left to ontology engineers. In this paper we present a method for term extraction and semantic interpretation, based on the use of corpora and existing lexical databases, such as WordNet.

In this paper, we present Lexical Episode Plots, a novel automated text-mining and visual analytics approach for exploratory text analysis. In particular, we first describe an algorithm for automatically annotating text regions to examine prominent themes within natural language texts. The algorithm is based on lexical chaining to find spans of text in which the frequency of a term is significa...

This paper investigates novel methods for incorporating syntactic information in probabilistic latent variable models of lexical choice and contextual similarity. The resulting models capture the effects of context on the interpretation of a word and in particular its effect on the appropriateness of replacing that word with a potentially related one. Evaluating our techniques on two datasets, ...

In studies of the acquisition of Japanese causatives, it has been reported that the morpheme –(s)ase is used at a relatively early period and at this point children can create sentences that have biclausal structures. However, if we closely look at the interpretation of the early utterances of causative sentences, we find that they are lexical causatives not syntactic causatives. Accordingly, w...

Planning-based approaches to reference provide a uniform treatment of linguistic decisions, from content selection to lexical choice. In this paper, we show how the issues of lexical ambiguity, vagueness, unspecific descriptions, ellipsis, and the interaction of subsective modifiers can be expressed using a belief-state planner modified to support context-dependent actions. Because the number o...

We present an approach to explicit, statistical, lexical-level out-of-vocabulary (OOV) word modeling for direct integration into the search space of a one-stage speech interpretation system. For this purpose, a generic pronunciation model for unknown words is derived from large pronunciation lexica and, optionally, word frequency knowledge. Known statistical language modeling (LM) methods are u...