Frustratingly Easy Domain Adaptation

Abstract

We describe an approach to domain adaptation that is appropriate exactly in the case when one has enough ``target'' data to do slightly better than just using only ``source'' data. Our approach is incredibly simple, easy to implement as a preprocessing step (10 lines of Perl!) and outperforms state-of-the-art approaches on a range of datasets. Moreover, it is trivially extended to a multi-domain adaptation problem, where one has data from a variety of different domains.

References in corpus (1)

• Domain Adaptation for Statistical Classifiers

Cited by in corpus (178)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Deep Domain Confusion: Maximizing for Domain Invariance
• On the Opportunities and Risks of Foundation Models
• Using Deep Learning and Google Street View to Estimate the Demographic Makeup of the US
• Marginalized Denoising Autoencoders for Domain Adaptation
• Person Re-Identification by Camera Correlation Aware Feature Augmentation
• Generalizing Across Domains via Cross-Gradient Training
• BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• A Comprehensive Survey on Transfer Learning
• Learning with Augmented Features for Heterogeneous Domain Adaptation
• Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
• Revisiting Few-sample BERT Fine-tuning
• Efficient Learning of Domain-invariant Image Representations
• Learn on Source, Refine on Target:A Model Transfer Learning Framework with Random Forests
• Text Readability Assessment for Second Language Learners
• Estimating individual treatment effect: generalization bounds and algorithms
• Learning to Generalize: Meta-Learning for Domain Generalization
• Return of Frustratingly Easy Domain Adaptation
• Domain Adaptive Neural Networks for Object Recognition
• A Unified Perspective on Multi-Domain and Multi-Task Learning
• What is the Essence of a Claim? Cross-Domain Claim Identification
• How Transferable are Neural Networks in NLP Applications?
• Bayesian Multitask Learning with Latent Hierarchies
• Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
• Transfer Learning for Hate Speech Detection in Social Media
• Learning from Multiple Outlooks
• One-Shot Adaptation of Supervised Deep Convolutional Models
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
• Sample-to-Sample Correspondence for Unsupervised Domain Adaptation
• Emotion Detection in Text: a Review
• Multi-modal Deep Analysis for Multimedia
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
• Private Federated Learning with Domain Adaptation
• Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
• Tackling Online Abuse: A Survey of Automated Abuse Detection Methods
• Visual Understanding via Multi-Feature Shared Learning with Global Consistency
• Fast Rates by Transferring from Auxiliary Hypotheses
• A Testbed for Cross-Dataset Analysis
• Construction of the Literature Graph in Semantic Scholar
• Compact Bilinear Pooling
• Bayesian Multitask Learning with Latent Hierarchies
• Variational Information Bottleneck for Effective Low-Resource Fine-Tuning
• Machine Learning in Cyber-Security - Problems, Challenges and Data Sets
• Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
• Simplified Neural Unsupervised Domain Adaptation
• A New PAC-Bayesian Perspective on Domain Adaptation
• Domain Adaptations for Computer Vision Applications
• Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
• Pretrained Transformers Improve Out-of-Distribution Robustness
• Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
• Which Clustering Do You Want? Inducing Your Ideal Clustering with Minimal Feedback
• When Unsupervised Domain Adaptation Meets Tensor Representations
• Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking
• Semi-Supervised Domain Adaptation with Non-Parametric Copulas
• Mind the Gap: Assessing Temporal Generalization in Neural Language Models
• Towards Robust and Privacy-preserving Text Representations
• Deep Multitask Learning for Semantic Dependency Parsing
• Semi-supervised representation learning via dual autoencoders for domain adaptation
• CrossNER: Evaluating Cross-Domain Named Entity Recognition
• Dataset Distillation
• Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
• Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimality
• Fine-Grained Car Detection for Visual Census Estimation
• Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
• Reuse and Adaptation for Entity Resolution through Transfer Learning
• ADAPT : Awesome Domain Adaptation Python Toolbox
• Towards generalisable hate speech detection: a review on obstacles and solutions
• Toward Mention Detection Robustness with Recurrent Neural Networks
• On the Sample Complexity of Stability Constrained Imitation Learning
• Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
• Optimizing Facial Expressions of an Android Robot Effectively: a Bayesian Optimization Approach
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• Feature Hashing for Large Scale Multitask Learning
• Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
• Multi-domain Neural Network Language Generation for Spoken Dialogue Systems
• Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
• Overcoming Language Variation in Sentiment Analysis with Social Attention
• Towards Domain Adaptation from Limited Data for Question Answering Using Deep Neural Networks
• Mutual Learning Network for Multi-Source Domain Adaptation
• Cross-domain Semantic Parsing via Paraphrasing
• Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
• Scalable Greedy Algorithms for Transfer Learning
• Projecting Embeddings for Domain Adaptation: Joint Modeling of Sentiment Analysis in Diverse Domains
• Regularized Multi-output Gaussian Convolution Process with Domain Adaptation
• Semantic Composition and Decomposition: From Recognition to Generation
• Relaxed Parameter Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
• Detecting dementia in Mandarin Chinese using transfer learning from a parallel corpus
• Hierarchical Adaptive Structural SVM for Domain Adaptation
• Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
• In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
• Respecting Domain Relations: Hypothesis Invariance for Domain Generalization
• Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
• Continual Domain-Tuning for Pretrained Language Models
• Neural Structural Correspondence Learning for Domain Adaptation
• Simpler but More Accurate Semantic Dependency Parsing
• Using Natural Language Processing and Qualitative Analysis to Intervene in Gang Violence: A Collaboration Between Social Work Researchers and Data Scientists
• Quizbowl: The Case for Incremental Question Answering
• Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning
• Learning Optimal Policies from Observational Data
• Strategies for Conceptual Change in Convolutional Neural Networks
• EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation
• Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
• Model-Based Domain Generalization
• Zero-Resource Cross-Domain Named Entity Recognition
• Joint Multi-Domain Learning for Automatic Short Answer Grading
• Label-Agnostic Sequence Labeling by Copying Nearest Neighbors
• Model Imitation for Model-Based Reinforcement Learning
• Data enriched linear regression
• SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation
• Selective Question Answering under Domain Shift
• Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
• Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation
• Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
• Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment
• An Extended Framework for Marginalized Domain Adaptation
• Driving Experience Transfer Method for End-to-End Control of Self-Driving Cars
• Generalisation in Named Entity Recognition: A Quantitative Analysis
• Probability Weighted Compact Feature for Domain Adaptive Retrieval
• Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
• Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning
• Marginalizing Corrupted Features
• Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction
• Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
• Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer
• Character-Aware Decoder for Translation into Morphologically Rich Languages
• Supervised Domain Adaptation using Graph Embedding
• Joint cross-domain classification and subspace learning for unsupervised adaptation
• Controlling biases and diversity in diverse image-to-image translation
• Multi-task Domain Adaptation for Sequence Tagging
• Towards Accurate Word Segmentation for Chinese Patents
• Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation
• Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension
• Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
• Types of Out-of-Distribution Texts and How to Detect Them
• Pre-train or Annotate? Domain Adaptation with a Constrained Budget
• What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Training
• DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction
• A Survey of Syntactic-Semantic Parsing Based on Constituent and Dependency Structures
• Domain Adaptation for Neural Networks by Parameter Augmentation
• From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
• Towards a continuous modeling of natural language domains
• Robust Visual Knowledge Transfer via EDA
• Factorial Hidden Markov Models for Learning Representations of Natural Language
• Metric Learning across Heterogeneous Domains by Respectively Aligning Both Priors and Posteriors
• Fast and Accurate Transferability Measurement for Heterogeneous Multivariate Data
• Cross-validation of matching correlation analysis by resampling matching weights
• Population-aware Hierarchical Bayesian Domain Adaptation
• Domain Adaptation: Overfitting and Small Sample Statistics
• Posterior Differential Regularization with f-divergence for Improving Model Robustness
• Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces
• Pretrained language model transfer on neural named entity recognition in Indonesian conversational texts
• Domain Adaptation for Infection Prediction from Symptoms Based on Data from Different Study Designs and Contexts
• Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis
• Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance
• #SarcasmDetection is soooo general! Towards a Domain-Independent Approach for Detecting Sarcasm
• Weakly Supervised Domain Detection
• Distributionally Robust Language Modeling
• Generalized Adaptive Dictionary Learning via Domain Shift Minimization
• Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation
• Towards Learning free Naive Bayes Nearest Neighbor-based Domain Adaptation
• Learning to see across Domains and Modalities
• Recommendation Chart of Domains for Cross-Domain Sentiment Analysis:Findings of A 20 Domain Study
• Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training
• Semi-supervised Stochastic Multi-Domain Learning using Variational Inference
• Aligning Hotel Embeddings using Domain Adaptation for Next-Item Recommendation
• Learning Word Embeddings with Domain Awareness
• Towards Explainable Fact Checking
• Coupled Support Vector Machines for Supervised Domain Adaptation
• To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning
• Cross-Domain Sparse Coding
• Transductive Learning with String Kernels for Cross-Domain Text Classification
• Cognitive Discriminative Mappings for Rapid Learning
• Unifying Multi-Domain Multi-Task Learning: Tensor and Neural Network Perspectives
• Cross-Lingual Adaptation using Structural Correspondence Learning