Adapting Meta Knowledge Graph Information For Multi-hop Reasoning Over Few-shot Relations | Awesome LLM Papers Add your paper to Awesome LLM Papers

Adapting Meta Knowledge Graph Information For Multi-hop Reasoning Over Few-shot Relations

Xin Lv, Yuxian Gu, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu . Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 2019 – 76 citations

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Datasets EMNLP Few Shot Has Code Interdisciplinary Approaches Question Answering Training Techniques

Multi-hop knowledge graph (KG) reasoning is an effective and explainable method for predicting the target entity via reasoning paths in query answering (QA) task. Most previous methods assume that every relation in KGs has enough training triples, regardless of those few-shot relations which cannot provide sufficient triples for training robust reasoning models. In fact, the performance of existing multi-hop reasoning methods drops significantly on few-shot relations. In this paper, we propose a meta-based multi-hop reasoning method (Meta-KGR), which adopts meta-learning to learn effective meta parameters from high-frequency relations that could quickly adapt to few-shot relations. We evaluate Meta-KGR on two public datasets sampled from Freebase and NELL, and the experimental results show that Meta-KGR outperforms the current state-of-the-art methods in few-shot scenarios. Our code and datasets can be obtained from https://github.com/ THU-KEG/MetaKGR.

Similar Work