Self-Supervised Knowledge Triplet Learning for Zero-Shot Question Answering
Pratyay Banerjee, Chitta Baral
Abstract
The aim of all Question Answering (QA) systems is to generalize to unseen questions. Current supervised methods are reliant on expensive data annotation. Moreover, such annotations can introduce unintended annotator bias, making systems focus more on the bias than the actual task. This work proposes Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs. We propose heuristics to create synthetic graphs for commonsense and scientific knowledge. We propose using KTL to perform zero-shot question answering, and our experiments show considerable improvements over large pre-trained transformer language models.
Topics & Concepts
HeuristicsComputer scienceArtificial intelligenceQuestion answeringTransformerAnnotationTask (project management)Supervised learningMachine learningNatural language processingEconomicsManagementArtificial neural networkQuantum mechanicsOperating systemVoltagePhysicsTopic ModelingDomain Adaptation and Few-Shot LearningMultimodal Machine Learning Applications