Named Entity-based Question-Answering Pair Generator

Abstract

In this paper, we demonstrate an approach for question-answering pair generation primarily based on named entities using TV series data. Our generator provides a task based pipeline abstraction, which can be interpreted by a simple method where a context paragraph is passed as an input argument to the pipeline and the output is generated based on the task selected. We currently implemented three tasks for the pipeline which includes the following - i) qg - single question generation, ii) multi-qa-qg for multiple QA pairs generation and iii) e2e-qg for end to end QA pair generation.