ACL Findings2023
Semi-Supervised Domain Adaptation for Emotion-Related Tasks
Mahshid Hosseini, Cornelia Caragea
Abstract
Semi-supervised domain adaptation (SSDA) adopts a model trained from a label-rich source domain to a new but related domain with a few labels of target data. It is shown that, in an SSDA setting, a simple combination of domain adaptation (DA) with semi-supervised learning (SSL) techniques often fails to effectively utilize the target supervision and cannot address distribution shifts across different domains due to the training data bias toward the source-labeled samples. In this paper, inspired by the co-learning of multiple classifiers for the computer vision tasks, we propose to decompose the SSDA framework for emotion-related tasks into two subcomponents of unsupervised domain adaptation (UDA) from the source to the target domain and semi-supervised learning (SSL) in the target domain where the two models iteratively teach each other by interchanging their high confident predictions. We further propose a novel data cartography-based regularization technique for pseudo-label denoising that employs training dynamics to further hone our models' performance. We release our code. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification cites Unsupervised Data Augmentation for Consistency Training
- JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification cites MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
- MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification cites JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification
- MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification cites MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
- Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation cites Semi-Supervised Domain Adaptation via Minimax Entropy
- LLM-Guided Co-Training for Text Classification cites JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification
- MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification cites Unsupervised Data Augmentation for Consistency Training
Cited by top-tier papers3
- JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text ClassificationHenry Peng Zou, Cornelia CarageaEMNLP 2023 · 13 citations
- MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text ClassificationIustin Sirbu, Robert-Adrian Popovici, Cornelia Caragea, Stefan Trausan-Matu et al.EMNLP 2025 · 1 citation
- LLM-Guided Co-Training for Text ClassificationMd Mezbaur Rahman, Cornelia CarageaEMNLP 2025
Builds on10
- Unsupervised Data Augmentation for Consistency TrainingQizhe Xie, Zihang Dai, Eduard H. Hovy, Thang Luong et al.NeurIPS 2020 · 2,774 citations
- Semi-Supervised Domain Adaptation via Minimax EntropyKuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell et al.ICCV 2019 · 725 citations
- MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text ClassificationJiaao Chen, Zichao Yang, Diyi YangACL 2020 · 340 citations
- Deep Co-Training with Task Decomposition for Semi-Supervised Domain AdaptationLuyu Yang, Yan Wang, Mingfei Gao, Abhinav Shrivastava et al.ICCV 2021 · 91 citations
- It Takes Two to Empathize: One to Seek and One to ProvideMahshid Hosseini, Cornelia CarageaAAAI 2021 · 53 citations
Related papers
- Semi-Supervised Domain Adaptation Based on Dual-Level Domain Mixing for Semantic SegmentationShuaijun Chen, Xu Jia, Jianzhong He, Yongjie Shi et al.CVPR 2021
- Semi-Supervised Domain Adaptation with Source Label AdaptationYu-Chu Yu, Hsuan-Tien LinCVPR 2023
- AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain AdaptationDavid Berthelot, Rebecca Roelofs, Kihyuk Sohn, Nicholas Carlini et al.ICLR 2022 · 180 citations
- GeT: Generative Target Structure Debiasing for Domain AdaptationCan Zhang, Gim Hee LeeICCV 2023 · 2 citations
- Improved Knowledge Transfer for Semi-supervised Domain Adaptation via Trico Training StrategyBa Hung Ngo, Yeon Jeong Chae, Jung Eun Kwon, Jae Hyeon Park et al.ICCV 2023 · 14 citations
