paper-with-me

Papers

Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding

2021-09-14 · Findings (EMNLP) 2021 11 · Shiyang Li, Semih Yavuz, Wenhu Chen, Xifeng Yan

Task-adaptive pre-training (TAPT) and Self-training (ST) have emerged as the major semi-supervised approaches to improve natural language understanding (NLU) tasks with massive amount of unlabeled data. However, it's unclear whether they learn similar representations or they can be effectively combined. In this paper, we show that TAPT and ST can be complementary with simple TFS protocol by following TAPT -> Finetuning -> Self-training (TFS) process. Experimental results show that TFS protocol can effectively utilize unlabeled data to achieve strong combined gains consistently across six datasets covering sentiment classification, paraphrase identification, natural language inference, named entity recognition and dialogue slot classification. We investigate various semi-supervised settings and consistently show that gains from TAPT and ST can be strongly additive by following TFS procedure. We hope that TFS could serve as an important semi-supervised baseline for future NLP studies.

📄 PDF Abstract BibTeX arXiv:2109.06466

Code (0)

등록된 구현이 없습니다.

Tasks

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Natural Language InferenceNatural Language UnderstandingParaphrase IdentificationSentiment AnalysisSentiment Classification

Similar Papers 제목 키워드 기반

SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning

2024-08-04 · Biqing Qi, Junqi Gao, Xinquan Chen, Dong Li 외

The ability of humans to rapidly learn new knowledge while retaining old memories poses a significant challenge for current deep learning models. To handle this challenge, we draw inspiration from human memory and learni…

Anomaly DetectionIncremental Learning

M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining

2021-09-09 · CVPR 2022 1 · Xiao Dong, Xunlin Zhan, Yangxin Wu, Yunchao Wei 외

Despite the potential of multi-modal pre-training to learn highly discriminative feature representations from complementary data modalities, current progress is being slowed by the lack of large-scale modality-diverse da…

Contrastive Learning

Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling

2019-03-28 · NAACL 2019 6 · Debjit Paul, Mittul Singh, Michael A. Hedderich, Dietrich Klakow

In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-reso…

Auxiliary LearningChunkingNER

CoMA: Complementary Masking and Hierarchical Dynamic Multi-Window Self-Attention in a Unified Pre-training Framework

2025-11-08 · Jiaxuan Li, Qing Xu, Xiangjian He, Ziyu Liu 외 arxiv

Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing…

Self-Supervised Learning

Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

2019-09-02 · ICCV 2019 10 · Seunghyeon Kim, Jaehoon Choi, Taekyung Kim, Changick Kim

Deep learning-based object detectors have shown remarkable improvements. However, supervised learning-based methods perform poorly when the train data and the test data have different distributions. To address the issue,…

Domain AdaptationObjectobject-detectionObject Detection+1