The symposium brought together researchers working on machine reading: systems that acquire knowledge from natural language text rather than from hand-built ontologies, and systems that improve their own reading ability as they go.
Sessions covered bootstrapped information extraction, grounded language acquisition, and the evaluation problem that still shadows the field - how to measure whether a machine has actually understood a passage rather than matched its surface patterns.
The programme material is preserved here because it is still cited in work on language grounding, which is now central to how robots interpret instructions on a factory floor.
This page preserves a historic coral-lab.org address. The original files are held offline; if you need them for citation or attribution, contact Coral Labs.