Better
The Better Extraction from Text Towards Enhanced Retrieval (BETTER) Program will develop methods for extracting increasingly fine-grained semantic information, with a focus of events in the form of who-did-what-to-whom-when-where, across multiple languages and problem domains.
This extracted information will be applied to an information retrieval task. An additional area of focus is human-in-the-loop computation. Performer systems will need the ability to incorporate human judgments for metrics such as relevancy and accuracy of extracted or retrieved information.