Question-aware memory network for multi-hop question answering in human-robot interaction

Xinmeng Li, Mamoun Alazab, Qian Li, Keping Yu, Quanjun Yin

Research output: Contribution to journalArticlepeer-review

1 Downloads (Pure)

Abstract

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.
Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalComplex & Intelligent Systems
DOIs
Publication statusE-pub ahead of print - Jul 2021

Fingerprint

Dive into the research topics of 'Question-aware memory network for multi-hop question answering in human-robot interaction'. Together they form a unique fingerprint.

Cite this