Early work in automatic problem-solving focused on what Newell has called “weak methods ” While these problemsolving strategies are quite general and are formally tractable, they are insufficient in practice for solving problems of any significant complexity. During the last decade, a number of techniques have been developed for improving the efficiency of these strategies. Since these techniqu...

When a case-based planner is retrieving a previous case in preparation for solving a new similar problem, it is often not aware of the implicit features of the new problem situation which determine if a particular case may be successfully applied. This means that some cases may be retrieved in error in that the case may fail to improve the planner’s performance. Retrieval may be incrementally i...

We propose a generic, memory-based approach for the detection of implicit semantic roles. While state-of-the-art methods for this task combine hand-crafted rules with specialized and costly lexical resources, our models use large corpora with automated annotations for explicit semantic roles only to capture the distribution of predicates and their associated roles. We show that memory-based lea...

We show how a general grammar may be automatically adapted for fast parsing of utterances from a specific domain by means of constituent pruning and grammar specialization based on explanation-based learning. These methods together give an order of magnitude increase in speed, and the coverage loss entailed by grammar specialization is reduced to approximately half that reported in previous wor...

The editorial provides a background for the special issue on Problem Based Learning and ICT and focuses on three core themes: Problem Based Learning (PBL) and its background and pedagogical principles; learning characteristics of information and communication technology (ICT); and intercultural perspectives. The editorial presents a Danish perspective on PBL based on the long tradition for PBL ...

An application of relational instance-based learning to the complex task of expressive music performance is presented. We investigate to what extent a machine can automatically build ‘expressive profiles’ of famous pianists using only minimal performance information extracted from audio CD recordings by pianists and the printed score of the played music. It turns out that the machine-generated ...

Systems that perform \generalization-to-N" in explanation-based learning generalize a proof tree by generalizing the shape of the tree, rather than simply changing constants to variables. This paper introduces a formal framework which can be used either to characterize or to specify the outputs of an algorithm for generalizing number. The framework consists of two desiderata, or desired propert...

We present our work on the identification of opinions and its components: the source, the topic and the message. We describe a rule-based system for which we achieved a recall of 74% and a precision of 94%. Experimentation with machine-learning techniques for the same task is currently underway.