Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types

TL;DR

This paper introduces a neural question generation model capable of creating questions from knowledge base triples involving unseen predicates and entity types, utilizing a novel encoder-decoder architecture with a part-of-speech copy mechanism, achieving state-of-the-art results.

Contribution

The paper proposes a new zero-shot question generation model that effectively handles unseen predicates and entity types using a novel copy mechanism and leveraging natural language corpus data.

Findings

Sets new state-of-the-art in zero-shot question generation

Outperforms previous models on benchmark datasets

Receives high scores in human evaluation

Abstract

We present a neural model for question generation from knowledge base triples in a "Zero-Shot" setup, that is generating questions for triples containing predicates, subject types or object types that were not seen at training time. Our model leverages triples occurrences in the natural language corpus in an encoder-decoder architecture, paired with an original part-of-speech copy action mechanism to generate questions. Benchmark and human evaluation show that our model sets a new state-of-the-art for zero-shot QG.