Controlling Information Aggregation for Complex Question Answering.

Complex question answering, the task of answering complex natural language questions that rely on inference, requires the aggregation of information from multiple sources. Automatic aggregation often fails because it combines semantically unrelated facts leading to bad inferences. This paper proposes methods to address this inference drift problem. In particular, the paper develops unsupervised and supervised mechanisms to control random walks on Open Information Extraction (OIE) knowledge graphs. Empirical evaluation on an elementary science exam benchmark shows that the proposed methods enables effective aggregation even over larger graphs and demonstrates the complementary value of information aggregation for answering complex questions.