Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering
This addresses the need for more robust and unbiased QA systems by reducing reliance on annotated data, though it appears incremental as it builds on existing self-supervised and knowledge graph methods.
The paper tackles the problem of generalizing to unseen questions in QA systems without expensive annotated data by proposing Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs, and shows considerable improvements over large pre-trained transformer models in zero-shot QA.
The aim of all Question Answering (QA) systems is to be able to generalize to unseen questions. Current supervised methods are reliant on expensive data annotation. Moreover, such annotations can introduce unintended annotator bias which makes systems focus more on the bias than the actual task. In this work, we propose 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 methods of how to use KTL to perform zero-shot QA and our experiments show considerable improvements over large pre-trained transformer models.