Asking It All: Generating Contextualized Questions for any Semantic Role

TL;DR

This paper introduces a novel task of role question generation, creating questions about semantic roles in a passage without relying on explicit answers, and presents a two-stage model that produces diverse, contextually appropriate questions.

Contribution

The paper proposes a new approach to question generation that does not depend on existing answers, using a two-stage model to produce diverse questions for semantic roles.

Findings

The model generates diverse, well-formed questions across a broad ontology.

It outperforms existing methods in question diversity and relevance.

The approach effectively handles implicit and explicit information in passages.

Abstract

Asking questions about a situation is an inherent step towards understanding it. To this end, we introduce the task of role question generation, which, given a predicate mention and a passage, requires producing a set of questions asking about all possible semantic roles of the predicate. We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage. Unlike most existing approaches to question generation, our approach does not require conditioning on existing answers in the text. Instead, we condition on the type of information to inquire about, regardless of whether the answer appears explicitly in the text, could be inferred from it, or should be sought elsewhere. Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.