... contents of query logs duringthe extraction of labeled classes of instances from Web documents, we acquire thousands (4,583, tobe exact) of open-domain classes covering a widerange of topics and ... period, symptoms, ] Query logs Web documents (1)(2)Figure 1: Overview of weakly-supervised extraction of class instances, class labels and class attributes from Web documents and query logsstudy ... informationextraction exploits both Web documents and query logs to acquire thousands of open-domain classes of instances, along with rel-evant sets of open-domain class attributes atprecision levels...