We describe a robust accurate domain-independent approach to statistical parsing incorporated into the new release of the ANLT toolkit, and publicly available as a research tool. The system has been used to parse many well known corpora in order to produce data for lexical acquisition efforts; it has also been used as a component in an open-domain question answering project. The performance of the system is competitive with that of statistical parsers using highly lexicalised parse selection models. However, we plan to extend the system to improve parse coverage, depth and accuracy.

Abstract not found

This article presents a new semanticbased transfer approach developed and applied within the Verbmobil Machine Translation project. We give an overview of the declarative transfer fo,'malism to- gether with its procedural realization. Our approach is discussed and compared with several other approaches f,'om the MT literature. The results presented in this article have been implemented and integrated into the Verbmobil system.

Abstract not found

Abstract. This article gives an overview of a new semantic-based transfer approach developed and applied within the Verbmobil Machine Translation project [22]. We present the declarative transfer formalism and discuss its implementation. The results presented in this paper have been integrated successfully in the Verbmobil system. 1

A large spoken dialogue translation system imposes both engineering and linguistic constraints on the way in which linguistic information is communicated between modules. We describe the design and use of interface terms, whose formal, functional and communicative role has been tested in a sequence of integrated systems and which have proven adequate to these constraints. 1

We present two approaches for syntactic and semantic transfer based on LFG f-structures and compare the results with existing co-description and restriction operator based approaches, focusing on aspects of ambiguity preserving transfer, complex cases of syntactic structural mismatches as well as on modularity and reusability. The two transfer approaches are interfaced with an existing, implemented transfer component (Verbmobil), by translating f-structures into a term language, and by interfacing f-structure representations with an existing semantic based transfer approach, respectively.

. I argue in favor of associating situations (events, episodes, eventualities, etc.) with arbitrarily complex sentences, not just atomic predicates, in NL interpretation. In that respect, a Situation Semantics approach to incorporating situations into semantic representations is preferable to a Davidsonian one. However, I will further argue that beyond the notion of truth or falsity of a sentence in a situation, as in Situation Semantics, we also need the notion of a sentence characterizing a situation, in order to deal adequately with causal relations mentioned or implied in NL texts. I propose a way of doing this that essentially reduces complex situations to joins of basic, Davidsonian ones, along with basic situations corresponding to negated predications. The resulting situational logic, called FOL**, captures many of the essential features of both Davidsonian and Situation Semantics approaches to representing the content of sentences describing situations. The proposed semantics ...

Communication using natural language is remarkably e cient, by allowing reuse (through the use of generative devices) of a nite vocabulary to describe a potentially innite set of situations. This vocabulary reuse contributes to words having many related senses (polysemy). Further, meanings can be relatively vague or precise � in other words, varying in their degree of speci cation of meaning. I suggest that these problems can be addressed by developing a knowledge representation which makes explicit the notion of granularity. As the grain size changes, we may fold certain distinctions, or split meanings more nely. In this paper, I formalize a theory of granularity and demonstrate how it can be applied to problems of meaning representation. Such a theory requires a world model which provides a rich sortal di erentiation of entities based on the distinctions made by natural language, including the representation of meronymic structure and rei-cation. Granularity will be represented in terms of structural operations de ned as abstractions. I illustrate how this applies to problems of polysemy and vagueness in nominalizations, where splitting and folding of meanings are particularly evident. 1

Current theories of aspect acknowledge the pervasiveness of verbs of variable telicity, and are designed to account both for why these verbs show such variability and for the complex conditions that give rise to telic and atelic interpretations. Previous work has identified several sets of such verbs, including incremental theme verbs,