Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction
This addresses the problem of handling complex multi-relation questions in human-robot interaction, though it appears incremental as it builds on existing memory network and embedding methods.
The paper tackles multi-hop question answering on knowledge graphs by proposing a question-aware memory network (QA2MN) that updates attention on question tokens during reasoning and incorporates graph context into embeddings, achieving state-of-the-art Hits@1 accuracy on PathQuestion and WorldCup2014 datasets.
Knowledge graph question answering is an important technology in intelligent human-robot interaction, which aims at automatically giving answer to human natural language question with the given knowledge graph. For the multi-relation question with higher variety and complexity, the tokens of the question have different priority for the triples selection in the reasoning steps. Most existing models take the question as a whole and ignore the priority information in it. To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process. In addition, we incorporate graph context information into knowledge graph embedding model to increase the ability to represent entities and relations. We use it to initialize the QA2MN model and fine-tune it in the training process. We evaluate QA2MN on PathQuestion and WorldCup2014, two representative datasets for complex multi-hop question answering. The result demonstrates that QA2MN achieves state-of-the-art Hits@1 accuracy on the two datasets, which validates the effectiveness of our model.