Popular models for Knowledge Graph Question Answering (KGQA), including semantic parsing and End-to-End (E2E) models, decode into a constrained space of KG relations. Al-though E2E models accommodate novel entities at test-time, this constraint means they cannot access novel relations, requiring expensive and time-consuming retraining whenever a new relation is added to the KG. We propose KG-Flex, a new architecture for E2E KGQA that instead decodes into a continuous embed-ding space of relations, which enables use of novel relations at test-time. KG-Flex is the first to support KG updates with entirely novel triples, free of retraining, while still supporting end-to-end training with simple, weak supervision of (Q, A) pairs. Our architecture saves on time, energy, and data resources for retraining, yet we retain performance on standard bench-marks. We further demonstrate zero-shot use of novel relations, achieving up to 82% of base-line hit@1 on three QA datasets. KG-Flex can also fine-tune, requiring significantly shorter time than full retraining; fine-tuning on target data for 10% of full training increases hit@1 to 89-100% of baseline.
Research areas
