NeuSTIP: A Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs

Ishaan Singh, Navdeep Kaur, Garima Gaur, Mausam .

Submission Type: Regular Long Paper

Submission Track: Information Extraction

Keywords: Information Extraction, Neuro-Symbolic Knowledge Graph Completion, Temporal Knowledge Graph Completion

TL;DR: We develop a novel neuro-symbolic TKGC method that represents the temporal information of TKGs in a temporal rule language it defines, and ascribes a novel confidence score to a candidate answer, which can be an entity or a time interval.

Abstract: Neuro-symbolic (NS) models for knowledge graph completion (KGC) combine the benefits of symbolic models (interpretable inference) with those of distributed representations (parameter sharing, high accuracy). While several NS models exist for KGs with static facts, there is limited work on temporal KGC (TKGC) for KGs where a fact is associated with a time interval. In response, we propose a novel NS model for TKGC called NeuSTIP, which performs link prediction and time interval prediction in a TKG. NeuSTIP learns temporal rules with Allen predicates, which ensure temporal consistency between neighboring predicates in the rule body. We further design a unique scoring function that evaluates the confidence of the candidate answers while performing link and time interval predictions by utilizing the learned rules. Our empirical evaluation on two time interval based TKGC datasets shows that our model shows competitive performance on link prediction and establishes a new state of the art on time prediction.

Submission Number: 3658