Controlling Information Aggregation for Complex Question Answering

  title={Controlling Information Aggregation for Complex Question Answering},
  author={Heeyoung Kwon and Harsh Trivedi and Peter Jansen and Mihai Surdeanu and Niranjan Balasubramanian},
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… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.

Open language learning

  • Mausam, M. Schmitz, S. Soderland, R. Bart, O. Etzioni
  • 2016

Standardized tests as a measure of AI

  • P. Jansen, N. Balasubramanian, M. Surdeanu, P. Clark
  • AI Mag
  • 2016
1 Excerpt

What ’ s in an explanation ? Characterizing knowledge and inference requirements for elementary science exams

  • Schmitz Mausam, M., S. Soderland, R. Bart, O. Etzioni
  • 2016

Similar Papers

Loading similar papers…