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

Anonymous

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.
We propose a new model for KBQA named RetinaQA that is robust against unaswerability. It uses discrimination instead of generation to better identify questions that do not have valid logical forms. Additionally, it complements KB-traversal based logical form retrieval with sketch-filling based logical form construction. This helps with questions that have valid logical forms but no data paths in the KB leading to an answer. We demonstrate that RetinaQA significantly outperforms adaptations of state-of-the-art KBQA models across answerable and unanswerable questions. Remarkably, it also establishes a new state-of-the art for answerable KBQA by surpassing existing models.

Paper Type: long

Research Area: Question Answering

Languages Studied: English

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.