MixQG: Neural Question Generation with Mixed Answer Types

Anonymous

Paper Link: https://openreview.net/forum?id=pUwtbIy9xiW

Paper Type: Short paper (up to four pages of content + unlimited references and appendices)

Abstract: Asking good questions is an essential ability for both human and machine intelligence. However, existing neural question generation approaches mainly focus on short factoid type of answers. In this paper, we introduce a neural question generator, MixQG, to bridge this gap. We combine nine question answering datasets with diverse answer types, including yes/no, multiple-choice, extractive, and abstractive answers, to train a single generative model. We show with empirical results that our model outperforms existing work in both seen and unseen domains, and can generate questions with different cognitive levels when conditioned on different answer types. We run a human evaluation study to assess the quality of generated questions and find that MixQG outperforms the next best model by 10%. Our code and model checkpoints will be released and integrated with the HuggingFace library to facilitate various downstream applications.

Presentation Mode: This paper will be presented virtually

Virtual Presentation Timezone: UTC-5

Copyright Consent Signature (type Name Or NA If Not Transferrable): Lidiya Murakhovs'ka

Copyright Consent Name And Address: Salesforce Research