mlsanityData to 7 Oct 2026

PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models

arXiv 2006.09075 ↗First posted 16 Jun 2020cs.CL cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

Pivot-based neural representation models have lead to significant progress in domain adaptation for NLP. However, previous works that follow this approach utilize only labeled data from the source domain and unlabeled data from the source and target domains, but neglect to incorporate massive unlabeled corpora that are not necessarily drawn from these domains. To alleviate this, we propose PERL: A representation learning model that extends contextualized word embedding models such as BERT with pivot-based fine-tuning. PERL outperforms strong baselines across 22 sentiment classification domain adaptation setups, improves in-domain model performance, yields effective reduced-size models and increases model stability.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 16; 2023: 6; 2024: 2; 2025: 2.

33 papers.

Sort:

By area:

  1. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  2. 2022Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulationscited by 44
  3. 2022DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptationcited by 36
  4. 2021UDALM: Unsupervised Domain Adaptation through Language Modelingcited by 33
  5. 2022Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Changecited by 18
  6. 2022Example-based Hypernetworks for Out-of-Distribution Generalizationcited by 16
  7. 2021Unsupervised Domain Adaptation with Adaptercited by 14
  8. 2021DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extractioncited by 11
  9. 2023Measuring the Robustness of NLP Models to Domain Shiftscited by 11
  10. 2022Representation Projection Invariance Mitigates Representation Collapsecited by 10
  11. 2022Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detectioncited by 7
  12. 2021Model Compression for Domain Adaptation through Causal Effect Estimationcited by 6
21 more
  1. 2021Target-Oriented Fine-tuning for Zero-Resource Named Entity Recognitioncited by 5
  2. 2022Explainable Misinformation Detection Across Multiple Social Media Platformscited by 5
  3. 2024How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?cited by 5
  4. 2021On the Universality of Deep Contextual Language Modelscited by 4
  5. 2022From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domainscited by 4
  6. 2022IDANI: Inference-time Domain Adaptation via Neuron-level Interventionscited by 4
  7. 2022Domain Confused Contrastive Learning for Unsupervised Domain Adaptationcited by 4
  8. 2022Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detectioncited by 3
  9. 2022Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learningcited by 3
  10. 2022Source-Free Domain Adaptation for Question Answering with Masked Self-trainingcited by 3
  11. 2023A Two-Stage Framework with Self-Supervised Distillation For Cross-Domain Text Classificationcited by 3
  12. 2024Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysiscited by 3
  13. 2022Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classificationcited by 2
  14. 2023Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLPcited by 2
  15. 2023TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classificationcited by 2
  16. 2025Multi-Domain Explainability of Preferencescited by 2
  17. 2022Domain Adaptation from Scratchcited by 0
  18. 2022Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detectioncited by 0
  19. 2023Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysiscited by 0
  20. 2023ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generationcited by 0
  21. 2025Similarity-Based Domain Adaptation with LLMscited by 0