Identifying Where to Focus in Reading Comprehension for Neural Question Generation

By Xinya Du, Claire Cardie. 2017

101 citations recorded by the source corpus.

A first step in the task of automatically generating questions for testing reading comprehension is to identify question-worthy sentences, i.e. sentences in a text passage that humans find it worthwhile to ask questions about. We propose a hierarchical neural sentence-level sequence tagging model for this task, which existing approaches to question generation have ignored. The approach is fully data-driven — with no sophisticated NLP pipelines or any hand-crafted rules/features — and compares favorably to a number of baselines when evaluated on the SQuAD data set. When incorporated into an existing neural question generation system, the resulting end-to-end system achieves state-of-the-art performance for paragraph-level question generation for reading comprehension.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Claire Cardie
2. Lidong Bing
3. Wai Lam
4. Xinya Du
5. Mitesh M. Khapra
6. Luo Si
7. Qian Yu
8. Mohit Bansal

In Natural Language Processing

1. Claire Cardie
2. Xinya Du
3. Lidong Bing
4. Mitesh M. Khapra
5. Wai Lam
6. Luo Si
7. Qian Yu
8. Qiong Zhang

Citations in the corpus

• Towards a Better Metric for Evaluating Question Generation Systems (2018, background): “…problem and create even more training data, there is growing interest in developing techniques that can automatically generate questions from a given source, say a document (Du et al., 2017; Du and Cardie, 2017), knowledge base (Reddy et al., 2017; Serban et al., 2016), or image (Li et al., 2017) .”
• Harvesting Paragraph-level Question-Answer Pairs from Wikipedia (2018, background): “Du and Cardie (2017) proposed a hierarchical neural sentence-level sequence tagging model for identifying question-worthy sentences in a text passage.”
• Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2019, methodology): “The preliminary neural QG models (Du et al., 2017; Zhou et al., 2017; Du and Cardie, 2017) outperform the rule-based methods relying on hand-craft features, and thereafter various models have been proposed to further improve the performance via incorporating question type (Dong et al., 2018),…”
• Low-Resource Generation of Multi-hop Reasoning Questions (2020, background): “Respec-tively, the neural model usually directly maps the text to question based on neural network (Du and Cardie, 2017), which is entirely data-driven with far less labor.”