2016/04/21 by Patrick Verga, Andrew McCallum, Verga, Patrick +1 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Artificial intelligence #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Information retrieval #Knowledge base #Limiting #Natural Language Processing Techniques #Natural language processing #Schema (genetic algorithms) #Theoretical computer science #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1604.06361
AKBC 2016 Workshop
arxiv created 2016/04/21 · openalex publication_date 2016/04/21 · arxiv updated 2016/04/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Universal schema jointly embeds knowledge bases and textual patterns to reason about entities and relations for automatic knowledge base construction and information extraction. In the past, entity pairs and relations were represented as learned vectors with compatibility determined by a scoring function, limiting generalization to unseen text patterns and entities. Recently, 'column-less' versions of Universal Schema have used compositional pattern encoders to generalize to all text patterns. In this work we take the next step and propose a 'row-less' model of universal schema, removing explicit entity pair representations. Instead of learning vector representations for each entity pair in our training set, we treat an entity pair as a function of its relation types. In experimental results on the FB15k-237 benchmark we demonstrate that we can match the performance of a comparable model with explicit entity pair representations using a model of attention over relation types. We further demonstrate that the model per- forms with nearly the same accuracy on entity pairs never seen during training.