Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy
This work addresses semantic question matching for open-domain applications, representing an incremental improvement over existing methods.
The paper tackles semantic question matching by proposing a hybrid technique that combines deep learning models with a two-layered question taxonomy, achieving state-of-the-art results on the POQR benchmark dataset.
In this paper, we propose a hybrid technique for semantic question matching. It uses our proposed two-layered taxonomy for English questions by augmenting state-of-the-art deep learning models with question classes obtained from a deep learning based question classifier. Experiments performed on three open-domain datasets demonstrate the effectiveness of our proposed approach. We achieve state-of-the-art results on partial ordering question ranking (POQR) benchmark dataset. Our empirical analysis shows that coupling standard distributional features (provided by the question encoder) with knowledge from taxonomy is more effective than either deep learning (DL) or taxonomy-based knowledge alone.