Learning to Generate Questions with Adaptive Copying Neural Networks

TL;DR

This paper introduces an adaptive copying neural network model that enhances question generation from text by integrating a copying mechanism into a bidirectional LSTM, outperforming existing methods.

Contribution

The paper presents a novel adaptive copying mechanism integrated into a bidirectional LSTM for improved question generation from sentences and paragraphs.

Findings

Outperforms state-of-the-art question generation models in BLEU and ROUGE scores

Demonstrates the effectiveness of the adaptive copying mechanism

Achieves more suitable question generation from input data

Abstract

Automatic question generation is an important problem in natural language processing. In this paper we propose a novel adaptive copying recurrent neural network model to tackle the problem of question generation from sentences and paragraphs. The proposed model adds a copying mechanism component onto a bidirectional LSTM architecture to generate more suitable questions adaptively from the input data. Our experimental results show the proposed model can outperform the state-of-the-art question generation methods in terms of BLEU and ROUGE evaluation scores.