Role-Aware Modeling for N-ary Relational Knowledge Bases
Authors:
Open Access
- 19 April 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2660-2671
Abstract
N-ary relational knowledge bases (KBs) represent knowledge with binary and beyond-binary relational facts. Especially, in an n-ary relational fact, the involved entities play different roles, e.g., the ternary relation PlayCharacterIn consists of three roles, Actor, Character and Movie. However, existing approaches are often directly extended from binary relational KBs, i.e., knowledge graphs, while missing the important semantic property of role. Therefore, we start from the role level, and propose a Role-Aware Modeling, RAM for short, for facts in n-ary relational KBs. RAM explores a latent space that contains basis vectors, and represents roles by linear combinations of these vectors. This way encourages semantically related roles to have close representations. RAM further introduces a pattern matrix that captures the compatibility between the role and all involved entities. To this end, it presents a multilinear scoring function to measure the plausibility of a fact composed by certain roles and entities. We show that RAM achieves both theoretical full expressiveness and computation efficiency, which also provides an elegant generalization for approaches in binary relational KBs. Experiments demonstrate that RAM outperforms representative baselines on both n-ary and binary relational datasets.Keywords
This publication has 24 references indexed in Scilit:
- A Review of Relational Machine Learning for Knowledge GraphsProceedings of the IEEE, 2015
- Type-Constrained Representation Learning in Knowledge Graphs2015
- Role Discovery in NetworksIEEE Transactions on Knowledge and Data Engineering, 2014
- Freebase2008
- Convex Multi-Task Feature LearningSSRN Electronic Journal, 2007
- Hierarchical Dirichlet ProcessesJournal of the American Statistical Association, 2006
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Automatic Labeling of Semantic RolesComputational Linguistics, 2002
- The Berkeley FrameNet Project1998
- Occam's RazorInformation Processing Letters, 1987