BoxLitE: A Faithful Knowledge Base Embedding Based on Convex Optimization
Knowledge base (KB) embeddings aim at combining the capability of classical knowledge graph embeddings to generalize the information present in facts, the ABox, with conceptual knowledge represented in an ontology language, the TBox. Several authors have recently explored the idea of mapping concepts to convex regions in a vector space. This is useful to represent hierarchies, typically present in TBoxes, since more general concepts can be mapped to larger regions, containing those regions associated with more specific concepts. However, the power of convexity is rarely leveraged during the actual learning tasks. Here, we introduce BoxLitE, a KB embedding model for DL-Lite$^{\mathcal{H}}$ that allows for convex optimization. We show that for any satisfiable DL-Lite$^{\mathcal{H}}$ KB, there is a BoxLitE embedding that is a weakly faithful model. As a proof of concept, we show how to formulate the KB embedding task as a convex optimization problem and how to obtain embeddings with such desirable faithfulness properties.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
KGEx: Explaining Knowledge Graph Embeddings via Subgraph Sampling and Knowledge Distillation
Despite being the go-to choice for link prediction on knowledge graphs, research on interpretability of knowledge graph embeddings (KGE) has been relatively unexplored. We present KGEx, a novel post-hoc method that expla…
Knowledge DistillationKnowledge Graph EmbeddingsKnowledge GraphsLink PredictionConvex Optimization Learning of Faithful Euclidean Distance Representations in Nonlinear Dimensionality Reduction
Classical multidimensional scaling only works well when the noisy distances observed in a high dimensional space can be faithfully represented by Euclidean distances in a low dimensional space. Advanced models such as Ma…
Dimensionality ReductionFaithful Embeddings for Knowledge Base Queries
The deductive closure of an ideal knowledge base (KB) contains exactly the logical queries that the KB can answer. However, in practice KBs are both incomplete and over-specified, failing to answer some queries that have…
Question AnsweringTowards Faithful Neural Table-to-Text Generation with Content-Matching Constraints
Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions. Most existing methods ignore the faithfulness between a generated text description and the original table, leadi…
Data-to-Text GenerationTable-to-Text GenerationText GenerationRHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the inp…
HallucinationRepresentation LearningRe-Ranking