paper-with-me

Papers

An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity Recognition

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Cross-lingual named entity recognition task is one of the critical problem for evaluating the potential transfer learning techniques on low resource languages. Knowledge distillation using pre-trained multilingual language models between source and target languages have shown their superiority. However, existing cross-lingual distillation models merely consider the potential transferability between two identical single tasks across both domain. Other possible auxiliary tasks to improve the learning performance have not been fully investigated. In this study, based on the knowledge distillation framework and multi-task learning, we introduce the similarity metric model as an auxiliary task to improve the cross-lingual NER performance on target domain. Specifically, an entity recognizer and a similarity evaluator teachers are first trained in parallel from the source domain. Then, two tasks in the student model are supervised by the two teachers simultaneously. Empirical studies on the datasets across 7 different languages confirm the effectiveness of the proposed model.

📄 PDF Abstract BibTeX

Code (1)

BDBC-KG-NLP/ACL2022_MTMT pytorch

Tasks

Cross-Lingual NERKnowledge DistillationMulti-Task Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation

2020-07-14 · Le Thanh Nguyen-Meidine, Atif Belal, Madhu Kiran, Jose Dolz 외

Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift between the distribution of unlabeled data from the target domain w.r.t. labeled data from the source domain. While the single-target UD…

Domain AdaptationKnowledge DistillationMulti-target Domain AdaptationSpecificity+1

An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity Recognition

2022-05-01 · ACL 2022 5 · Zhuoran Li, Chunming Hu, Xiaohui Guo, Junfan Chen 외

Cross-lingual named entity recognition task is one of the critical problems for evaluating the potential transfer learning techniques on low resource languages. Knowledge distillation using pre-trained multilingual langu…

Cross-Lingual NERKnowledge DistillationMulti-Task Learningnamed-entity-recognition+4

CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector

2024-12-16 · Tianheng Qiu, Ka Lung Law, Guanghua Pan, Jufei Wang 외

Unsupervised domain adaptive (UDA) algorithms can markedly enhance the performance of object detectors under conditions of domain shifts, thereby reducing the necessity for extensive labeling and retraining. Current doma…

Contrastive LearningData Augmentationobject-detectionObject Detection

Contrastive Knowledge Amalgamation for Unsupervised Image Classification

2023-07-27 · Shangde Gao, Yichao Fu, Ke Liu, Yuqiang Han

Knowledge amalgamation (KA) aims to learn a compact student model to handle the joint objective from multiple teacher models that are are specialized for their own tasks respectively. Current methods focus on coarsely al…

Classificationimage-classificationImage ClassificationUnsupervised Image Classification

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

2023-12-05 · CVPR 2024 1 · Arun Reddy, William Paul, Corban Rivera, Ketul Shah 외

In this work, we tackle the problem of unsupervised domain adaptation (UDA) for video action recognition. Our approach, which we call UNITE, uses an image teacher model to adapt a video student model to the target domain…

Action RecognitionDomain AdaptationTemporal Action LocalizationUnsupervised Domain Adaptation