Question Generation for Question Answering

By Nan Duan, Duyu Tang, Peng Chen, M. Zhou. 2017

295 citations recorded by the source corpus.

This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data. The contribution of the paper is 2-fold: First, two types of question generation approaches are proposed, one is a retrieval-based method using convolution neural network (CNN), the other is a generation-based method using recurrent neural network (RNN); Second, we show how to leverage the generated questions to improve existing question answering systems. We evaluate our question generation method for the answer sentence selection task on three benchmark datasets, including SQuAD, MS MARCO, and WikiQA. Experimental results show that, by using generated questions as an extra signal, significant QA improvement can be achieved.

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

In Natural Language Processing

Citations in the corpus

Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (2019, methodology): “…1: An examples of the “semantic drift” issue in Question Generation (“Gt” is short for “ground truth”). task to QA, QG can not only be used to augment QA datasets (Duan et al., 2017), but can also be applied in conversation and education systems (Heilman and Smith, 2010; Lindberg et al., 2013).”
Towards a Better Metric for Evaluating Question Generation Systems (2018, background): “Given the practical importance of AQG and its potential to inﬂuence research in QA, it is not surprising that there has been proliﬁc work in this ﬁeld in the past one year itself (Jain et al., 2017; Li et al., 2017; Zhang et al., 2017; Du et al., 2017; Duan et al., 2017).”
Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks (2018, methodology): “On MS MARCO dataset, we compare the BLEU 4 scores reported by (Duan et al., 2017) in Table 4.”
Harvesting Paragraph-level Question-Answer Pairs from Wikipedia (2018, background): “Finally, Duan et al. (2017) investigated how to use question generation to help improve question answering systems on the sentence selection subtask.”
Generating Fact Checking Briefs (2020, neutral): “Unlike previous question generation models (Du et al., 2017; Duan et al., 2017; Tang et al., 2017; Zhao et al., 2018) that generate based on an answer, we treat question generation closer to structured planning — laying out the format for the entire brief.”
Policy Compliance Detection via Expression Tree Inference (2022, methodology): “Question generation (Heilman and Smith, 2010) of this form is typically employed as part of a pipeline for question-answering (Duan et al., 2017; Wang et al., 2020; Lewis et al., 2021) or for generating questions for fact-checking summary briefs (Hassan et al., 2017; Jimenez, 2017; Fan et al.,…”
Low-Resource Generation of Multi-hop Reasoning Questions (2020, background): “…including providing practice exercises from course materials for educational purposes (Lindberg et al., 2013), initiating the dialog system by asking questions (Mostafazadeh et al., 2017), and reducing the labor cost of creating large-scale labeled samples for the QA task (Duan et al., 2017).”
Improving Neural Question Generation using Answer Separation (2018, methodology): “(Duan et al. 2017) crawled an external QA dataset and generated questions from it through their retrieval-based and generation-based question generation methods.”
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering (2020, methodology): “ating synthetic questions to complete a dataset has shown to improve QA performances (Duan et al., 2017; Alberti et al., 2019).”
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering (2021, background): “In the past few years, research on automatic question generation from text passages has received growing attention [150], [151], [152].”
Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data (2019, background): “This is a crucial yet challenging task in NLP that has received growing attention due to its application in improving question answering systems (Duan et al., 2017; Tang et al., 2017, 2018), providing material for educational purposes (Heilman and Smith, 2010), and helping conversational systems to…”
MTG: A Benchmark Suite for Multilingual Text Generation (2021, background): “Question generation (QG) targets at generating a correct question for a given passage and its answer (Duan et al., 2017).”
Answer-based Adversarial Training for Generating Clarification Questions (2019, background): “Most previous work on question generation has been on generating reading comprehension style questions i.e. questions that ask about information present in a given text (Heilman, 2011; Rus et al., 2010, 2011; Duan et al., 2017).”
Investigating Pretrained Language Models for Graph-to-Text Generation (2020, background): “This task is important for NLP applications such as dialogue generation (Moon et al., 2019) and question answering (Duan et al., 2017).”
Learning to Collaborate for Question Answering and Asking (2018, background): “This work relates to recent studies which attempt to improve the performance of a discriminative QA model with generative models (Wang et al., 2017; Yang et al., 2017; Dong et al., 2017; Duan et al., 2017).”
Multi-Agent Dual Learning (2019, background): “…and applied to many applications including neural machine translation (NMT) (He et al., 2016; Xia et al., 2017a;b), image-to-image translation (Zhu et al., 2017; Yi et al., 2017; Luo et al., 2017), question answering (Duan et al., 2017; Sun et al., 2019) and image captioning (Huang et al., 2018).”
Self-Training for Jointly Learning to Ask and Answer Questions (2018, background): “However, recent papers build on neural network approaches such as seq2seq (Du et al., 2017; Tang et al., 2017; Zhou et al., 2017), CNNs and RNNs (Duan et al., 2017) for QG.”
Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2019, background): “, reading comprehension or question answering (Duan et al., 2017) with various motivations including improving auxiliary task performance (Duan et al.”
QURIOUS: Question Generation Pretraining for Text Generation (2020, methodology): “For answer-focused question generation, earlier work (Duan et al., 2017; Subramanian et al., 2018; Nema et al., 2019) has mostly focused on the factoid-based question answering dataset such as SQuAD (Rajpurkar et al., 2016).”