EMNLP Findings2020
Regularization of Distinct Strategies for Unsupervised Question Generation
Junmo Kang, Giwon Hong, Haritz Puerto San Roman, Sung-Hyon Myaeng
Abstract
Unsupervised question answering (UQA) has been proposed to avoid the high cost of creating high-quality datasets for QA. One approach to UQA is to train a QA model with questions generated automatically. However, the generated questions are either too similar to a word sequence in the context or too drifted from the semantics of the context, thereby making it difficult to train a robust QA model. We propose a novel regularization method based on teacher-student architecture to avoid bias toward a particular question generation strategy and modulate the process of generating individual words when a question is generated. Our experiments demonstrate that we have achieved the goal of generating higher-quality questions for UQA across diverse QA datasets and tasks. We also show that this method can be useful for creating a QA model with few-shot learning.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers2
Builds on1
Related papers
- Harvesting and Refining Question-Answer Pairs for Unsupervised QAZhongli Li, Wenhui Wang, Li Dong, Furu Wei et al.ACL 2020 · 29 citations
- Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word GenerationQifan Wang, Li Yang, Xiaojun Quan, Fuli Feng et al.EMNLP 2022 · 5 citations
- AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph WalkingYuxiang Nie, Heyan Huang, Wei Wei, Xian-Ling MaoACL Findings 2023 · 2 citations
- AutoEQA: Auto-Encoding Questions for Extractive Question AnsweringStalin Varanasi, Saadullah Amin, Guenter NeumannEMNLP Findings 2021 · 2 citations
- An Empirical Comparison of LM-based Question and Answer Generation MethodsAsahi Ushio, Fernando Alva-Manchego, José Camacho-ColladosACL Findings 2023 · 25 citations
