Show simple item record

dc.contributor.authorZhang, Chuxu
dc.contributor.authorYu, Lu
dc.contributor.authorSaebi, Mandana
dc.contributor.authorJiang, Meng
dc.contributor.authorChawla, Nitesh
dc.date.accessioned2021-03-03T06:25:17Z
dc.date.available2021-03-03T06:25:17Z
dc.date.issued2020
dc.identifier.citationZhang, C., Yu, L., Saebi, M., Jiang, M., & Chawla, N. (2020). Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases. Findings of the Association for Computational Linguistics: EMNLP 2020. doi:10.18653/v1/2020.findings-emnlp.51
dc.identifier.doi10.18653/v1/2020.findings-emnlp.51
dc.identifier.urihttp://hdl.handle.net/10754/667823
dc.description.abstractMulti-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths. The current methods usually require sufficient training data (fact triples) for each query relation, impairing their performances over few-shot relations (with limited triples) which are common in knowledge base. To this end, we propose FIRE, a novel few-shot multi-hop relation learning model. FIRE applies reinforcement learning to model the sequential steps of multi-hop reasoning, besides performs heterogeneous structure encoding and knowledge-aware search space pruning. The meta-learning technique is employed to optimize model parameters that could quickly adapt to few-shot relations. Empirical study on two datasets demonstrate that FIRE outperforms state-of-the-art methods
dc.description.sponsorshipThis work was supported in part by National Science Foundation grants CCI-1925607 and IIS1849816. We also thank the anonymous reviewers for their valuable comments and helpful suggestions.
dc.publisherAssociation for Computational Linguistics (ACL)
dc.relation.urlhttps://www.aclweb.org/anthology/2020.findings-emnlp.51
dc.rightsArchived with thanks to Association for Computational Linguistics
dc.titleFew-Shot Multi-Hop Relation Reasoning over Knowledge Bases
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.conference.dateNovember 16 - 20, 2020
dc.conference.nameAssociation for Computational Linguistics
dc.eprint.versionPre-print
dc.contributor.institutionBrandeis University
dc.contributor.institutionUniversity of Notre Dame
kaust.personYu, Lu


This item appears in the following Collection(s)

Show simple item record