Toward Automated Prior Choice

Toward Automated Component Adaptation

This paper explores the use of specification matching to discover and select component adaptation strategies. This is done within a formal framework that integrates specification-based component retrieval with a formal architecture representation to support component retrieval and adaptation. The key to integration is determining the relationship between what components are potentially reusable...

On the choice of a sparse prior.

An emerging paradigm analyses in what respect the properties of the nervous system reflect properties of natural scenes. It is hypothesized that neurons form sparse representations of natural stimuli: each neuron should respond strongly to some stimuli while being inactive upon presentation of most others. For a given network, sparse representations need fewest spikes, and thus the nervous syst...

Plans Toward Automated Chat Summarization

We describe the beginning stages of our work on summarizing chat, which is motivated by our observations concerning the information overload of US Navy watchstanders. We describe the challenges of summarizing chat and focus on two chat-specific types of summarizations we are interested in: thread summaries and temporal summaries. We then discuss our plans for addressing these challenges and eva...

Toward Automated Component-Level Evaluation

Automated component-level evaluation of information retrieval is discussed. The advantages of such an approach are considered, as well as the requirements for implementing it. Acceptance of such systems by researchers is discussed.

Toward Practical Automated Program Understanding