mlsanityData to 7 Oct 2026

Semi-Supervised QA with Generative Domain-Adaptive Nets

arXiv 1702.02206 ↗First posted 7 Feb 2017cs.CL cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

We study the problem of semi-supervised question answering----utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework, the Generative Domain-Adaptive Nets. In this framework, we train a generative model to generate questions based on the unlabeled text, and combine model-generated questions with human-generated questions for training question answering models. We develop novel domain adaptation algorithms, based on reinforcement learning, to alleviate the discrepancy between the model-generated data distribution and the human-generated data distribution. Experiments show that our proposed framework obtains substantial improvement from unlabeled text.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 8; 2023: 5; 2024: 2.

27 papers.

Sort:

By area:

  1. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  2. 2021Math Word Problem Generation with Mathematical Consistency and Problem Context Constraintscited by 27
  3. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25
  4. 2023LIQUID: A Framework for List Question Answering Dataset Generationcited by 19
  5. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  6. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  7. 2022Which Shortcut Solution Do Question Answering Models Prefer to Learn?cited by 9
  8. 2023Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challengescited by 9
  9. 2021Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlapcited by 8
  10. 2021OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approachcited by 7
  11. 2021Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Datacited by 6
  12. 2021Improving Question Answering Performance Using Knowledge Distillation and Active Learningcited by 6
15 more
  1. 2022QA Is the New KR: Question-Answer Pairs as Knowledge Basescited by 6
  2. 2022Evaluation of Question Answering Systems: Complexity of judging a natural languagecited by 5
  3. 2024Transfer Learning for Finetuning Large Language Modelscited by 5
  4. 2021MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domainscited by 4
  5. 2021Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Taskscited by 4
  6. 2022DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlogcited by 3
  7. 2021ASAT: Adaptively Scaled Adversarial Training in Time Seriescited by 2
  8. 2022PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GANcited by 2
  9. 2022QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptationcited by 2
  10. 2024ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videoscited by 2
  11. 2023UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimizationcited by 1
  12. 2021Analysis and evaluation of Deep Learning based Super-Resolution algorithms to improve performance in Low-Resolution Face Recognitioncited by 0
  13. 2021Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systemscited by 0
  14. 2023Unsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Modelcited by 0
  15. 2023Perturbation-based Active Learning for Question Answeringcited by 0