Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss

TL;DR

This paper presents a neural question generation model for knowledge bases that incorporates diversified contexts and an answer-aware loss to produce more accurate, predicate-expressive, and definitive questions, achieving state-of-the-art results.

Contribution

It introduces a novel neural encoder-decoder model with multi-level copy mechanisms and an answer-aware loss for improved question generation over knowledge bases.

Findings

Achieves state-of-the-art performance on question generation tasks.

Generated questions effectively express predicates and yield definitive answers.

Model outperforms previous methods in accuracy and relevance.

Abstract

We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be definitive. In this paper, we strive toward the above two issues via incorporating diversified contexts and answer-aware loss. Specifically, we propose a neural encoder-decoder model with multi-level copy mechanisms to generate such questions. Furthermore, the answer aware loss is introduced to make generated questions corresponding to more definitive answers. Experiments demonstrate that our model achieves state-of-the-art performance. Meanwhile, such generated question can express the given predicate and correspond to a definitive answer.