paper-with-me

Papers

Making Pre-trained Language Models Better Few-shot Learners

2020-12-31 · ACL 2021 5 · Tianyu Gao, Adam Fisch, Danqi Chen

The recent GPT-3 model (Brown et al., 2020) achieves remarkable few-shot performance solely by leveraging a natural-language prompt and a few task demonstrations as input context. Inspired by their findings, we study few-shot learning in a more practical scenario, where we use smaller language models for which fine-tuning is computationally efficient. We present LM-BFF--better few-shot fine-tuning of language models--a suite of simple and complementary techniques for fine-tuning language models on a small number of annotated examples. Our approach includes (1) prompt-based fine-tuning together with a novel pipeline for automating prompt generation; and (2) a refined strategy for dynamically and selectively incorporating demonstrations into each context. Finally, we present a systematic evaluation for analyzing few-shot performance on a range of NLP tasks, including classification and regression. Our experiments demonstrate that our methods combine to dramatically outperform standard fine-tuning procedures in this low resource setting, achieving up to 30% absolute improvement, and 11% on average across all tasks. Our approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning.

📄 PDF Abstract BibTeX arXiv:2012.15723

Code (9)

princeton-nlp/LM-BFF 공식 구현 pytorch
abdumaa/hiqualprop pytorch
alrope123/prompt-waywardness pytorch
facebookresearch/perfect pytorch
hannight/amulap pytorch
matthewcym/sflm pytorch
ucsb-nlp-chang/promptboosting pytorch
ukplab/emnlp2021-prompt-ft-heuristics pytorch
zhengxiangshi/powerfulpromptft pytorch

Tasks

Few-Shot LearningZero-Shot Text Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Multi-Head Attention 설명 없음
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
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…

Similar Papers 제목 키워드 기반

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

2021-08-30 · ICLR 2022 4 · Ningyu Zhang, Luoqiu Li, Xiang Chen, Shumin Deng 외

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the…

Language ModelingLanguage ModellingPrompt Engineering

Making Pretrained Language Models Good Long-tailed Learners

2022-05-11 · Chen Zhang, Lei Ren, Jingang Wang, Wei Wu 외

Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a…

Classification

LMTurk: Few-Shot Learners as Crowdsourcing Workers

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Vast efforts have been devoted to creating high-performance few-shot learners, i.e., large-scale pretrained language models (PLMs) that perform well with little downstream task training data. Training PLMs has incurred …

LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework

2021-12-14 · Findings (NAACL) 2022 7 · Mengjie Zhao, Fei Mi, Yasheng Wang, Minglei Li 외

Vast efforts have been devoted to creating high-performance few-shot learners, i.e., large-scale pretrained language models (PLMs) that perform well with little downstream task training data. Training PLMs has incurred s…

Active LearningLanguage ModelingLanguage Modelling

Beyond Prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

2022-10-29 · Yu Fei, Ping Nie, Zhao Meng, Roger Wattenhofer 외

Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated self-training pipelines, hindering thei…

ClusteringSentenceSentence EmbeddingsSentiment Analysis+5