Feeding Software Agents with Web Information

Abstract

Abstract. Many software agents require information that is available in web documents. Unfortunately, the existing proposals to learn extraction rules are tightly coupled with the learning component and do not result in resilient rules. We present a novel approach that leverages neural networks and has proven to be very resilient.

ARIEX: Automated ranking of information extractors

“…Summing up, we think that we have contributed to the state of the art with a solid method to evaluate, compare, and rank information extraction proposals. It was our experience regarding devising new information extractors that motivated us to work on it [7,31,37,[66][67][68]. Unfortunately, that experience also revealed that there are two obstacles in practice: the lack of public datasets and the unavailability of public implementations.…”