Both greedy and domain-oriented REG algorithms have significant strengths but tend to perform poorly according to humanlikeness criteria as measured by, e.g., Dice scores. In this work we describe an attempt to combine both perspectives into a single attribute selection strategy to be used as part of the Dale & Reiter Incremental algorithm in the REG Challenge 2008, and the results in both Furniture and People domains.

No abstract

No abstract

We present a follow-up of our previous frequency-based greedy attribute selection strategy. The current version takes into account also the instructions given to the participants of TUNA trials regarding the use of location information, showing an overall improvement on string-edit distance values driven by the results on the Furniture domain.

No abstract