Embedding Symbolic Knowledge into Deep Networks
In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augmented Graph Convolutional Network (GCN). To generate semantically-faithful embeddings, we develop techniques to recognize node heterogeneity, and semantic regularization that incorporate structural constraints into the embedding. Experiments show that our approach improves the performance of models trained to perform entailment checking and visual relation prediction. Interestingly, we observe a connection between the tractability of the propositional theory representation and the ease of embedding. Future exploration of this connection may elucidate the relationship between knowledge compilation and vector representation learning.
Code (1)
Tasks
Graph EmbeddingRelation PredictionRepresentation LearningSimilar Papers 제목 키워드 기반
Word Sense Disambiguation as a Game of Neurosymbolic Darts
Word Sense Disambiguation (WSD) is one of the hardest tasks in natural language understanding and knowledge engineering. The glass ceiling of 80% F1 score is recently achieved through supervised deep-learning, enriched b…
Knowledge GraphsNatural Language UnderstandingWord Sense DisambiguationGeometric Relational Embeddings
Relational representation learning transforms relational data into continuous and low-dimensional vector representations. However, vector-based representations fall short in capturing crucial properties of relational dat…
Knowledge GraphsRepresentation LearningQuantum Embedding of Knowledge for Reasoning
Statistical Relational Learning (SRL) methods are the most widely used techniques to generate distributional representations of the symbolic Knowledge Bases (KBs). These methods embed any given KB into a vector space by …
Logical ReasoningRelational ReasoningHow the (Tensor-) Brain uses Embeddings and Embodiment to Encode Senses and Symbols
The Tensor Brain (TB) has been introduced as a computational model for perception and memory. This paper provides an overview of the TB model, incorporating recent developments and insights into its functionality. The TB…
Embedding Symbolic Temporal Knowledge into Deep Sequential Models
Sequences and time-series often arise in robot tasks, e.g., in activity recognition and imitation learning. In recent years, deep neural networks (DNNs) have emerged as an effective data-driven methodology for processing…
Action RecognitionActivity RecognitionGraph Neural NetworkImitation Learning+2