paper-with-me

홈 › Papers

Prompt Tuning for Discriminative Pre-trained Language Models

2022-05-23 · Findings (ACL) 2022 5 · Yuan YAO, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, Jianyong Wang

Recent works have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing (NLP) tasks. However, to the best of our knowledge, existing works focus on prompt-tuning generative PLMs that are pre-trained to generate target tokens, such as BERT. It is still unknown whether and how discriminative PLMs, e.g., ELECTRA, can be effectively prompt-tuned. In this work, we present DPT, the first prompt tuning framework for discriminative PLMs, which reformulates NLP tasks into a discriminative language modeling problem. Comprehensive experiments on text classification and question answering show that, compared with vanilla fine-tuning, DPT achieves significantly higher performance, and also prevents the unstable problem in tuning large PLMs in both full-set and low-resource settings. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/DPT.

📄 PDF Abstract BibTeX arXiv:2205.11166

Code (1)

thunlp/dpt 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingQuestion Answeringtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at +1-888-829-0881 or +1(805) 330 (4056). You can also use the live chat…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

SEP: Self-Enhanced Prompt Tuning for Visual-Language Model

2024-05-24 · Hantao Yao, Rui Zhang, Lu Yu, Yongdong Zhang 외

Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as th…

Language ModelingLanguage Modelling

Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification

2022-10-23 · Zhipeng Xie, Yahe Li

This paper proposes a novel prompt-based finetuning method (called DLM-SCS) for few-shot text classification by utilizing the discriminative language model ELECTRA that is pretrained to distinguish whether a token is ori…

Few-Shot Text ClassificationLanguage ModelingLanguage Modellingtext-classification+1

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction

2024-01-25 · Jiangmeng Li, Fei Song, Yifan Jin, Wenwen Qiang 외

As a novel and effective fine-tuning paradigm based on large-scale pre-trained language models (PLMs), prompt-tuning aims to reduce the gap between downstream tasks and pre-training objectives. While prompt-tuning has yi…

Domain Adaptation

Generative Prompt Tuning for Relation Classification

2022-10-22 · Jiale Han, Shuai Zhao, Bo Cheng, Shengkun Ma 외

Using prompts to explore the knowledge contained within pre-trained language models for downstream tasks has now become an active topic. Current prompt tuning methods mostly convert the downstream tasks to masked languag…

ClassificationLanguage ModelingLanguage ModellingMasked Language Modeling+4

VladVA: Discriminative Fine-tuning of LVLMs

2024-12-05 · CVPR 2025 1 · Yassine Ouali, Adrian Bulat, Alexandros Xenos, Anestis Zaganidis 외

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often…

Image-text RetrievalRepresentation LearningText Retrieval