In the project "Procedural Dialogue Models" being carried on at the University of Bielefeld we have developed an Incremental multilevel parsing formalism to reconstruct task-oriented dialogues. A major difficulty we have had to overcome is that the dialogues are real ones with numerous ungrammatical utterances. The approach we have devised to cope with this problem is reported here. I THE INCRE...

This paper is concerned with the semantic interpretation of natural English sentences by a computerized question-answering system, and specifically with tne problems of interpreting and using quantification in such systems. Those issues are presented and discussed from the perspective of four different natural language understanding systems with which the author has been involved. The presentat...

A spoken language understanding (SLU) system is described. It generates hypotheses of conceptual constituents with a translation process. This process is performed by finite state transducers (FST) which accept word patterns from a lattice of word hypotheses generated by an Automatic Speech Recognition (ASR) system. FSTs operate in parallel and may share word hypotheses at their input. Semantic...

MESA (Multi-Ethnic Study of Atherosclerosis) is an observational cohort study to determine the prevalence, correlates, and progression of subclinical cardiovascular disease. MESA participants were 45 to 84 years of age and were asymptomatic of clinical cardiovascular disease in 2000 to 2002 at recruitment and were studied in 6 centers in the United States. This ambitious setting offered the uni...

We describe a technique for the robust interpretation of newswire texts which uses semantic role information about verb complements together with a general co-reference mechanism to extend the constituent structure analysis produced by a partial parser. This technique has the advantage that failure to nd a spanning parse of an entire sentence does not necessarily preclude correct semantic inter...

This paper presents a lexical model dedicated to the semantic representation and interpretation of individual words in unrestricted text, where sense discrimination is difficult to assess. We discuss the need of a lexicon including local inference mechanisms and cooperating with as many other knowledge sources (about syntax, semantics and pragmatics) as possible. We suggest a minimalist represe...