We present ERIC, an affective embodied agent for realtime commentary in many domains. The underlying architecture is rulebased, generic, and lightweight
Extending a machine learning based coreference resolution system with a feature capturing automatically generated information about semantic roles improves its performance.
Language modeling is an effective and theoretically attractive probabilistic framework for text information retrieval. The basic idea of this approach is to estimate a language mo...
Several mathematical distances between probabilistic languages have been investigated in the literature, motivated by applications in language modeling, computational biology, syn...
In this case study I argue for the usage of a machine-oriented controlled natural language as interface language to knowledge systems. Instead of using formal languages that are di...