# Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering

arXiv: https://arxiv.org/abs/2004.11892 · HTML: https://mlsanity.com/paper/2004.11892/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2020.

## Built on by (most cited first, 30 of 39)

- [Retrieval-Augmented Generation for Natural Language Processing: A Survey](https://mlsanity.com/paper/2407.13193/) (2024)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER](https://mlsanity.com/paper/2108.13655/) (2021)
- [Self-Supervised Test-Time Learning for Reading Comprehension](https://mlsanity.com/paper/2103.11263/) (2021)
- [Improving Unsupervised Question Answering via Summarization-Informed Question Generation](https://mlsanity.com/paper/2109.07954/) (2021)
- [PaniniQA: Enhancing Patient Education Through Interactive Question Answering](https://mlsanity.com/paper/2308.03253/) (2023)
- [TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method](https://mlsanity.com/paper/2109.09617/) (2021)
- [Improving Biomedical Information Retrieval with Neural Retrievers](https://mlsanity.com/paper/2201.07745/) (2022)
- [Generating Information-Seeking Conversations from Unlabeled Documents](https://mlsanity.com/paper/2205.12609/) (2022)
- [Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization](https://mlsanity.com/paper/2210.09175/) (2022)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Synthetic Question Value Estimation for Domain Adaptation of Question Answering](https://mlsanity.com/paper/2203.08926/) (2022)
- [MAUPQA: Massive Automatically-created Polish Question Answering Dataset](https://mlsanity.com/paper/2305.05486/) (2023)
- [QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance](https://mlsanity.com/paper/2204.13921/) (2022)
- [Relation-Guided Pre-Training for Open-Domain Question Answering](https://mlsanity.com/paper/2109.10346/) (2021)
- [Unsupervised Natural Language Inference Using PHL Triplet Generation](https://mlsanity.com/paper/2110.08438/) (2021)
- [Evaluation of Question Answering Systems: Complexity of judging a natural language](https://mlsanity.com/paper/2209.12617/) (2022)
- [Automatic Document Sketching: Generating Drafts from Analogous Texts](https://mlsanity.com/paper/2106.07192/) (2021)
- [Two-Step Question Retrieval for Open-Domain QA](https://mlsanity.com/paper/2205.09393/) (2022)
- [EHRTutor: Enhancing Patient Understanding of Discharge Instructions](https://mlsanity.com/paper/2310.19212/) (2023)
- [Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision](https://mlsanity.com/paper/2107.08582/) (2021)
- [DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition](https://mlsanity.com/paper/2211.08104/) (2022)
- [ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation](https://mlsanity.com/paper/2310.11282/) (2023)
- [Graph Guided Question Answer Generation for Procedural Question-Answering](https://mlsanity.com/paper/2401.13594/) (2024)
- [GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning](https://mlsanity.com/paper/2404.09163/) (2024)
- [Ask to Understand: Question Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2203.09073/) (2022)
- [PREME: Preference-based Meeting Exploration through an Interactive Questionnaire](https://mlsanity.com/paper/2205.02370/) (2022)
- [PIE-QG: Paraphrased Information Extraction for Unsupervised Question Generation from Small Corpora](https://mlsanity.com/paper/2301.01064/) (2023)
- [Evaluating Prompt-based Question Answering for Object Prediction in the Open Research Knowledge Graph](https://mlsanity.com/paper/2305.12900/) (2023)
- [When More Retrieval Hurts: Retrieval-Augmented Code Review Generation](https://mlsanity.com/paper/2511.05302/) (2025)

## Abstract (arXiv)

Question Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has been to fine-tune a pretrained language model on a task-specific labeled dataset. This paradigm, however, relies on scarce, and costly to obtain, large-scale human-labeled data. We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sentence improves downstream QA performance by allowing the model to learn more complex context-question relationships. Training a QA model on this data gives a relative improvement over a previous unsupervised model in F1 score on the SQuAD dataset by about 14%, and 20% when the answer is a named entity, achieving state-of-the-art performance on SQuAD for unsupervised QA.