mlsanityData to 7 Oct 2026

Synthetic Target Domain Supervision for Open Retrieval QA

arXiv 2204.09248 ↗First posted 20 Apr 2022cs.CL cs.IRcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR) -- a state-of-the-art (SOTA) open domain neural retrieval model -- on closed and specialized target domains such as COVID-19, and find that it lags behind standard BM25 in this important real-world setting. To make DPR more robust under domain shift, we explore its fine-tuning with synthetic training examples, which we generate from unlabeled target domain text using a text-to-text generator. In our experiments, this noisy but fully automated target domain supervision gives DPR a sizable advantage over BM25 in out-of-domain settings, making it a more viable model in practice. Finally, an ensemble of BM25 and our improved DPR model yields the best results, further pushing the SOTA for open retrieval QA on multiple out-of-domain test sets.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 20 Apr 2022.

Builds on

30 of 40 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  9. 2017Billion-scale similarity search with GPUscited by 2,477
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  11. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  12. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
18 more
  1. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  3. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  4. 2019Publicly Available Clinical BERT Embeddingscited by 995
  5. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  6. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  8. 2020CORD-19: The COVID-19 Open Research Datasetcited by 179
  9. 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
  10. 2020XOR QA: Cross-lingual Open-Retrieval Question Answeringcited by 121
  11. 2019Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Indexcited by 64
  12. 2019A BERT Baseline for the Natural Questionscited by 33
  13. 2017Neural Domain Adaptation for Biomedical Question Answeringcited by 30
  14. 2020Multi-Stage Pre-training for Low-Resource Domain Adaptationcited by 24
  15. 2018Simple and Effective Semi-Supervised Question Answeringcited by 22
  16. 2020RikiNet: Reading Wikipedia Pages for Natural Question Answeringcited by 21
  17. 2020Rapidly Bootstrapping a Question Answering Dataset for COVID-19cited by 14
  18. 2020Answering Questions on COVID-19 in Real-Timecited by 11

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 1.

6 papers.

  1. 2023InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankerscited by 14
  2. 2022Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrievalcited by 5
  3. 2023PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Developmentcited by 4
  4. 2023ReFIT: Relevance Feedback from a Reranker during Inferencecited by 2
  5. 2024Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorizationcited by 0
  6. 2025MURR: Model Updating with Regularized Replay for Searching a Document Streamcited by 0