mlsanityData to 7 Oct 2026

DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction

arXiv 2109.00571 ↗First posted 1 Sep 2021cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

The rise of pre-trained language models has yielded substantial progress in the vast majority of Natural Language Processing (NLP) tasks. However, a generic approach towards the pre-training procedure can naturally be sub-optimal in some cases. Particularly, fine-tuning a pre-trained language model on a source domain and then applying it to a different target domain, results in a sharp performance decline of the eventual classifier for many source-target domain pairs. Moreover, in some NLP tasks, the output categories substantially differ between domains, making adaptation even more challenging. This, for example, happens in the task of aspect extraction, where the aspects of interest of reviews of, e.g., restaurants or electronic devices may be very different. This paper presents a new fine-tuning scheme for BERT, which aims to address the above challenges. We name this scheme DILBERT: Domain Invariant Learning with BERT, and customize it for aspect extraction in the unsupervised domain adaptation setting. DILBERT harnesses the categorical information of both the source and the target domains to guide the pre-training process towards a more domain and category invariant representation, thus closing the gap between the domains. We show that DILBERT yields substantial improvements over state-of-the-art baselines while using a fraction of the unlabeled data, particularly in more challenging domain adaptation setups.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 15 of its 42 references that are in the map. First posted on arXiv 1 Sep 2021.

Builds on

15 of 42 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2015Image-based Recommendations on Styles and Substitutescited by 702
  6. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  7. 2015The Variational Fair Autoencodercited by 223
  8. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  9. 2020Neural Unsupervised Domain Adaptation in NLP---A Surveycited by 142
  10. 2020SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysiscited by 54
  11. 2016Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysiscited by 35
  12. 2020PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Modelscited by 33
3 more
  1. 2019Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learningcited by 22
  2. 2016Neural Structural Correspondence Learning for Domain Adaptationcited by 19
  3. 2019Simplified Neural Unsupervised Domain Adaptationcited by 10

Built on by

Cited by year

Citing papers per year: 2022: 9; 2023: 2.

11 papers.

  1. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  2. 2022DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptationcited by 36
  3. 2022On the Domain Adaptation and Generalization of Pretrained Language Models: A Surveycited by 22
  4. 2022Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Changecited by 18
  5. 2022Example-based Hypernetworks for Out-of-Distribution Generalizationcited by 16
  6. 2023Measuring the Robustness of NLP Models to Domain Shiftscited by 11
  7. 2023NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Textscited by 9
  8. 2022Understanding Domain Learning in Language Models Through Subpopulation Analysiscited by 4
  9. 2022Source-Free Domain Adaptation for Question Answering with Masked Self-trainingcited by 3
  10. 2022Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysiscited by 1
  11. 2022Domain Adaptation from Scratchcited by 0