Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
By: Simon Welz, Lucie Flek, Akbar Karimi
Potential Business Impact:
Helps computers answer complex questions better.
Hyperbolic representations are effective in modeling knowledge graph data which is prevalently used to facilitate multi-hop reasoning. However, a rigorous and detailed comparison of the two spaces for this task is lacking. In this paper, through a simple integration of hyperbolic representations with an encoder-decoder model, we perform a controlled and comprehensive set of experiments to compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning. Our results show that the former consistently outperforms the latter across a diverse set of datasets. In addition, through an ablation study, we show that a learnable curvature initialized with the delta hyperbolicity of the utilized data yields superior results to random initializations. Furthermore, our findings suggest that hyperbolic representations can be significantly more advantageous when the datasets exhibit a more hierarchical structure.
Similar Papers
Reinforcement Learning in hyperbolic space for multi-step reasoning
Machine Learning (CS)
Helps computers solve hard math problems faster.
A group-theoretic framework for machine learning in hyperbolic spaces
Machine Learning (CS)
Makes computer learning faster and smarter.
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
Machine Learning (CS)
Keeps old computer memories useful for new programs.