RETINAQA : A Knowledge Base Question Answering Model Robust to both Answerable and Unanswerable Questions

arXiv:2403.10849v1 Announce Type: new
Abstract: State-of-the-art KBQA models assume answerability of questions. Recent research has shown that while these can be adapted to detect unaswerability with suitable training and thresholding, this comes at the expense of accuracy for answerable questions, and no single model is able to handle all categories of unanswerability. We propose a new model for KBQA named RetinaQA that is robust against unaswerability. It complements KB-traversal based logical form retrieval with sketch-filling based logical form construction. This …

abstract accuracy art arxiv cs.cl knowledge knowledge base question question answering questions research robust state thresholding training type