shizhediao/awesome-domain-adaptation-nlp

domain adaptation in NLP

awesome-domain-adaptation-NLP

domain adaptation in NLP

This repo is a collection of AWESOME things about domain adaptation in NLP, including papers, code, etc. Feel free to star and fork. Please feel free to pull requests or report issues.

Contents

• awsome-domain-adaptation
• Contents
• Papers
  • Survey
  • Theory
• Code Repos
• Lectures and Tutorials
• Other Resources

Papers

ACL 2021

• Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach [ACL 2021 Long] [pdf][code]
• Domain-Adaptive Pretraining Methods for Dialogue Understanding [ACL 2021 Short] [pdf]
• Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU [ACL 2021 Long] [pdf]
• Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains [ACL 2021 Findings Long] [pdf][code]
• Preview, Attend and Review Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking [ACL 2021 Short] [pdf]
• Crowdsourcing Learning as Domain Adaptation A Case Study on Named Entity Recognition [ACL 2021 Long] [pdf][code]
• Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking [ACL 2021 Short] [pdf][code]
• Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning [ACL 2021 Short] [pdf][code]
• Unsupervised Out-of-Domain Detection via Pre-trained Transformers [ACL 2021 Long] [pdf][code]
• Adapt-and-Distill Developing Small, Fast and Effective Pretrained Language Models for Domains [ACL 2021 Findings Long] [pdf][code]

NAACL 2021

• Meta-Learning for Domain Generalization in Semantic Parsing [NAACL 2021] [pdf][code]
• UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus [NAACL 2021] [pdf][code]
• DART: Open-Domain Structured Data Record to Text Generation [NAACL 2021] [pdf][code]
• OodGAN: Generative Adversarial Network for Out-of-Domain Data [NAACL 2021 Industry track] [pdf]
• Leaving No Valuable Knowledge Behind: Weak Supervision with Self-training and Domain-specific Rules [NAACL 2021] [pdf][code]
• QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization [NAACL 2021] [pdf][code]
• UDALM: Unsupervised Domain Adaptation through Language Modeling [NAACL 2021] [pdf][code]

EMNLP 2020

• Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains [EMNLP 2020] [pdf][code]
• Transformer Based Multi-Source Domain Adaptation [EMNLP 2020] [pdf][code]
• Multi-Stage Pre-training for Low-Resource Domain Adaptation [EMNLP 2020] [pdf]
• Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining [EMNLP 2020] [pdf]
• Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses [EMNLP 2020] [pdf][code]
• Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training [EMNLP 2020] [pdf]
• End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems [EMNLP 2020] [pdf]
• Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models [EMNLP 2020] [pdf][code]
• An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training [EMNLP 2020] [pdf][code]
• MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models [EMNLP 2020 main conference] [pdf]

Survey

• Neural Unsupervised Domain Adaptation in NLP—A Survey [arXiv 2020 May] [pdf] [code]
• 迁移学习简明手册 Jindong Wang et al. Transfer Learning Tutorial. [pdf]

Theory

Negative Transfer

• Characterizing and Avoiding Negative Transfer [CVPR 2019] [pdf]

Data Selection

• Reinforced Training Data Selection for Domain Adaptation [ACL 2019] [pdf] [code]
• Entropy-based Training Data Selection for Domain Adaptation [COLING 2012] [pdf]

Pretraining-based

• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing [arXiv 2020 Aug] [pdf] [code]
• Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks [ACL 2020] [pdf] [code]
• Using Similarity Measures to Select Pretraining Data for NER [NAACL 2019] [pdf] [code]
• Unsupervised Domain Clusters in Pretrained Language Models [ACL 2020] [pdf] [code]
• Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling [EMNLP 2019] [pdf] [code]

Alignment-based

• Curriculum Learning for Domain Adaptation in Neural Machine Translation [NAACL 2019] [pdf] [code]
• To Annotate or Not? Predicting Performance Drop under Domain Shift [EMNLP 2019] [pdf] [code]
• Active Adversarial Domain Adaptation [WACV 2020] [pdf]
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning [NeurIPS 2019] [pdf] [code]
• Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits [AAAI 2020] [pdf]
• Bayesian Uncertainty Matching for Unsupervised Domain Adaptation [IJCAI 2019] [pdf]
• Unsupervised Domain Adaptation via Calibrating Uncertainties [CVPR Workshop 19] [pdf]

Code Repos

Unsupervised domain adaptation method for relation extraction [code]
Unsupervised domain adaptation with BERT for Amazon food product reviews sentiment analysis. [code]

Lectures and Tutorials

Other Resources