Leveraging Structured Metadata for Improving Question Answering on the Web

Xinya Du1, Ahmed Hassan Awadallah2, Adam Fourney2, Robert Sim2, Paul Bennett2, Claire Cardie1
1Cornell University, 2Microsoft Research


We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking. We propose a neural passage selection model that leverages metadata information with a fine-grained encoding strategy, which learns the representation for metadata predicates in a hierarchical way. The models are evaluated on the MS MARCO (Nguyen et al., 2016) and Recipe-MARCO datasets. Results show that our models significantly outperform baseline models, which do not incorporate metadata. We also show that the fine-grained encoding’s advantage over other strategies for encoding the metadata.