Word graphs are able to represent a large number of different utterance hypotheses in a very compact manner. However, usually they contain a huge amount of redundancy in terms of ...
Starting from descriptions of French connectives (in particular "donc"---therefore), on the one hand, and aspectual properties of French tenses pass4 simple and imparfai...
This paper examines the phenomenon of consonant spreading in Arabic stems. Each spreading involves a local surface copying of an underlying consonant, and, in certain phonological...
We present core aspects of a fully implemented generation component in a multilingual speechto-speech dialogue translation system. Its design was particularly influenced by the ne...
Tilman Becker, Wolfgang Finkler, Anne Kilger, Pete...
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
We present an approach to anaphora resolution based on a focusing algorithm, and implemented within an existing MUC (Message Understanding Conference) Information Extraction syste...
Saliha Azzam, Kevin Humphreys, Robert J. Gaizauska...
In this paper we sketch an approach for Natural Language parsing. Our approach is an example-based approach, which relies mainly on examples that already parsed to their represent...
We present an algorithm for bilingual word alignment that extends previous work by treating multi-word candidates on a par with single words, and combining some simple assumptions...