Large practical NLP applications require robust analysis components that can effectively handle input that is disfluent or extra-grammatical. The effectiveness and efficiency of any robust parser are a direct function of three main factors: (1) Flexibility: what types of disfluencies and deviations from the grammar can the parser handle?; (2) Search: How does the parser search the space of possible interpretations, and what techniques are applied to prune the search space?; and (3) Parse Selection and Disambiguation: What methods and resources are used to evaluate and rank potential parses and sub-parses, and how does the parser cope with the extreme levels of ambiguity introduced by its flexibility parameters? In this chapter we describe our investigations on how to balance flexibility and efficiency in the context of two different robust parsers - a GLR parser and a left corner Chart parser - both based on a unification-augmented context-free grammar formalism. We demonstrate how the...

The goal of the CLARITY project is to explore the use of discourse structure in the understanding of conversational speech. Within project CLARITY we aim to develop automatic classifiers for three levels of discourse structure in Spanish telephone conversations: speech acts, dialogue games, and discourse segments. This paper presents our first results and research plans in three areas: definition of discourse structure units and manual annotation of CALL-HOME SPANISH, speech recognition, and automated segmentation and labeling of speech acts.

Both genetic algorithms and neural networks are machine learning techniques inspired by nature. By mimicking, although in a simplied way, biological processes, new alternatives in problem solving can be explored. We are interested in the application of these strategies in the eld of natural language processing. Here we provide an overview of previously published material in this area. We trace which domains of natural language processing have been investigated with evolutionary or neural strategies, discuss approaches and experiments, and provide an introduction to the literature. 1 Introduction Both evolutionary algorithms and articial neural networks mimick aspects of biological processes. In this section we introduce these methods and point to the general literature. 1.1 Evolutionary Computing The idea of using evolutionary computation as a problem solving technique exists since the 1950s (Box, 1957), (Bledsoe, 1961), (Fraser, 1957). Since then, four major approaches ha...