2020/04/25 by Wanjun Zhong, Duyu Tang, Zhong, Wanjun +9
Computer Science · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2004.12057
9 pages
arxiv created 2020/04/25 · openalex publication_date 2020/04/25 · arxiv updated 2020/04/28 · openalex created_date 2020/05/01 · openalex updated_date 2026/07/28
We study question answering over a dynamic textual environment. Although neural network models achieve impressive accuracy via learning from input-output examples, they rarely leverage various types of knowledge and are generally not interpretable. In this work, we propose a graph-based approach, where a heterogeneous graph is automatically built with factual knowledge of the context, temporal knowledge of the past states, and logical knowledge that combines human-curated knowledge bases and rule bases. We develop a graph neural network over the constructed graph, and train the model in an end-to-end manner. Experimental results on a benchmark dataset show that the injection of various types of knowledge improves a strong neural network baseline. An additional benefit of our approach is that the graph itself naturally serves as a rational behind the decision making.