Relational Graph Representation Learning for Open-Domain Question Answering
arXiv:1910.08249
Abstract
We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model can learn contextual representation by jointly learning and updating the query, knowledge graph, and document representations. The experiments suggest that our model achieves state-of-the-art on the WebQuestionsSP benchmark.
NeurIPS 2019 Workshop on Graph Representation Learning
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Graph Neural Networks: A Review of Methods and Applications
- Neural Natural Language Inference Models Enhanced with External Knowledge
- Variational Reasoning for Question Answering with Knowledge Graph
- Deep Learning on Graphs: A Survey
- Augmenting Neural Machine Translation with Knowledge Graphs