paper-with-me

Papers

Self-Evolution Learning for Discriminative Language Model Pretraining

2023-05-24 · Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao

Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence meaning, where some of them are more worthy to be predicted. Therefore, various masking strategies (e.g., entity-level masking) are proposed, but most of them require expensive prior knowledge and generally train from scratch without reusing existing model weights. In this paper, we present Self-Evolution learning (SE), a simple and effective token masking and learning method to fully and wisely exploit the knowledge from data. SE focuses on learning the informative yet under-explored tokens and adaptively regularizes the training by introducing a novel Token-specific Label Smoothing approach. Experiments on 10 tasks show that our SE brings consistent and significant improvements (+1.43~2.12 average scores) upon different PLMs. In-depth analyses demonstrate that SE improves linguistic knowledge learning and generalization.

📄 PDF Abstract BibTeX arXiv:2305.15275

Code (1)

whu-zqh/se4plms 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMasked Language ModelingmodelSentence

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

SCRIPT: Self-Critic PreTraining of Transformers

2021-06-01 · NAACL 2021 4 · Erik Nijkamp, Bo Pang, Ying Nian Wu, Caiming Xiong

We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text. The popular masked language modeling (MLM) pretraining methods like BERT replace some tokens with [MASK] and an encoder is t…

Language ModelingLanguage ModellingMasked Language ModelingRepresentation Learning

Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE

2022-12-04 · Qihuang Zhong, Liang Ding, Yibing Zhan, Yu Qiao 외

This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmar…

Common Sense Reasoningcoreference-resolutionCoreference ResolutionLanguage Modeling+5

Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?

2025-03-10 · Yuru Jia, Valerio Marsocci, Ziyang Gong, Xue Yang 외

Self-supervised learning (SSL) has revolutionized representation learning in Remote Sensing (RS), advancing Geospatial Foundation Models (GFMs) to leverage vast unlabeled satellite imagery for diverse downstream tasks. C…

Contrastive LearningImage GenerationRepresentation LearningSelf-Supervised Learning+1

Pretraining for Conditional Generation with Pseudo Self Attention

2019-05-21 · Anonymous

Large pretrained language representation models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that finetune a pretrained model. Howe…

Conditional Text GenerationNatural Language UnderstandingText GenerationTransfer Learning

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

2026-05-05 · Shuyue Stella Li, Rui Xin, Teng Xiao, Yike Wang 외 arxiv

Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotations, proprietary models, or scalar reward models) to produce reward …