This paper demonstrates that generating arguments in natural language requires at an abstract level, and that the ate abstraction cannot be captured by approaches based solely upo...
The paper describes a novel computational tool for multiple concept learning. Unlike previous approaches, whose major goal is prediction on unseen instances rather than the legibi...
We discuss an interactive approach to robust interpretation in a large scale speech-to-speech translation system. Where other interactive approaches to robust interpretation have ...
Current models of story comprehension have three major deficiencies: (1) lack of experimental support for the inference processes they involve (e.g. reliance on prediction); (2) i...
The problem of transforming a lattice into a non-deterministic finite state automaton is non-trivial. We present a transformation algorithm which tracks, for each node of an autom...
Mark Seligman, Christian Boitet, Boubaker Meddeb-H...