The CLEARS (Computational Linguistics Education and Research for Semantics) tool provides a graphical interface allowing interactive construction of semantic representations in a variety of different formalisms, and using several construction methods. CLEARS was developed as part of the FraCaS project which was designed to encourage convergence between different semantic formalisms, such as Montague-Grammar, DRT, and Situation Semantics. The CLEARS system is freely available on the WWW from http://coli.uni-sb.de/~clears/clears.html
The paper discusses how compositional semantics is implemented in the Verbmobil speech-to-speech translation system using LUD, a description language for underspecified discourse representation structures. The description language and its formal interpretation in DRT are described as well as its implementation together with the architecture of the system's entire syntactic-semantic processing module. We show that a linguistically sound theory and formalism can be properly implemented in a system with (near) real-time requirements.
In this paper, we discuss the question whether phrasal comparatives should be given a direct interpretation, or require an analysis as elliptic constructions, and answer it with Yes and No. The most adequate analysis of wide reading attributive (WRA) comparatives seems to be as cases of ellipsis, while a direct (but asymmetric) analysis fits the data for narrow scope attributive comparatives. The question whether it is a syntactic or a semantic process which provides the missing linguistic material in the complement of WRA comparatives is also given a complex answer: Linguistic context is accessed by combining a reconstruction operation and a mechanism of anaphoric reference. The analysis makes only few and straightforward syntactic assumptions. In part, this is made possible because the use of Generalized Functional Application as a semantic operation allows us to model semantic composition in a flexible way.