paper-with-me

홈 › Papers

Dynamic Data Selection for Curriculum Learning via Ability Estimation

2020-10-30 · Findings of the Association for Computational Linguistics 2020 · John P. Lalor, Hong Yu

Curriculum learning methods typically rely on heuristics to estimate the difficulty of training examples or the ability of the model. In this work, we propose replacing difficulty heuristics with learned difficulty parameters. We also propose Dynamic Data selection for Curriculum Learning via Ability Estimation (DDaCLAE), a strategy that probes model ability at each training epoch to select the best training examples at that point. We show that models using learned difficulty and/or ability outperform heuristic-based curriculum learning models on the GLUE classification tasks.

📄 PDF Abstract BibTeX arXiv:2011.00080

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Curriculum Manager for Source Selection in Multi-Source Domain Adaptation

2020-07-02 · ECCV 2020 8 · Luyu Yang, Yogesh Balaji, Ser-Nam Lim, Abhinav Shrivastava

The performance of Multi-Source Unsupervised Domain Adaptation depends significantly on the effectiveness of transfer from labeled source domain samples. In this paper, we proposed an adversarial agent that learns a dyna…

Domain AdaptationMulti-Source Unsupervised Domain AdaptationUnsupervised Domain Adaptation

Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation

2019-06-03 · Wei Wang, Isaac Caswell, Ciprian Chelba

Noise and domain are important aspects of data quality for neural machine translation. Existing research focus separately on domain-data selection, clean-data selection, or their static combination, leaving the dynamic i…

Machine TranslationTransfer LearningTranslation

Dynamically Composing Domain-Data Selection with Clean-Data Selection by ``Co-Curricular Learning'' for Neural Machine Translation

2019-07-01 · ACL 2019 7 · Wei Wang, Isaac Caswell, Ciprian Chelba

Noise and domain are important aspects of data quality for neural machine translation. Existing research focus separately on domain-data selection, clean-data selection, or their static combination, leaving the dynamic i…

Machine TranslationTransfer LearningTranslation

A Psychology-based Unified Dynamic Framework for Curriculum Learning

2024-08-09 · Guangyu Meng, Qingkai Zeng, John P. Lalor, Hong Yu

Directly learning from examples of random difficulty levels is often challenging for both humans and machine learning models. A more effective strategy involves exposing learners to examples in a progressive order, from …

Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion

2026-02-01 · Chunming He, Rihan Zhang, Fengyang Xiao, Dingming Zhang 외 arxiv

Biological learning proceeds from easy to difficult tasks, gradually reinforcing perception and robustness. Inspired by this principle, we address Context-Entangled Content Segmentation (CECS), a challenging setting wher…

Object Detection