Enabling Efficient Question Answer Retrieval via Hyperbolic Neural Networks

Many state-of-the-art deep learning models for question answer retrieval are highly complex, often having a huge number of parameters or complicated word interaction mechanisms. This paper studies if it is possible to achieve equally competitive performance with smaller and faster neural architectures. Overall, our proposed approach is a simple neural network that performs question-answer matching and ranking in Hyperbolic space. We show that QA embeddings learned in Hyperbolic space results in highly competitive performance on multiple benchmarks, outperforming models with significantly much larger parameters. Our proposed approach (90K parameters) remains competitive to models with millions of parameters such as Attentive Pooling BiLSTMs or Multi-Perspective Convolutional Neural Networks (MP-CNN).