Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385570752> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4385570752 abstract "In recent years, there has been significant progress in developing pre-trained language models for NLP. However, these models often struggle when fine-tuned on small datasets. To address this issue, researchers have proposed various adaptation approaches. Prompt-based tuning is arguably the most common way, especially for larger models. Previous research shows that adding contrastive learning to prompt-based fine-tuning is effective as it helps the model generate embeddings that are more distinguishable between classes, and it can also be more sample-efficient as the model learns from positive and negative examples simultaneously. One of the most important components of contrastive learning is data augmentation, but unlike computer vision, effective data augmentation for NLP is still challenging. This paper proposes LM-CPPF, Contrastive Paraphrasing-guided Prompt-based Fine-tuning of Language Models, which leverages prompt-based few-shot paraphrasing using generative language models, especially large language models such as GPT-3 and OPT-175B, for data augmentation. Our experiments on multiple text classification benchmarks show that this augmentation method outperforms other methods, such as easy data augmentation, back translation, and multiple templates." @default.
- W4385570752 created "2023-08-05" @default.
- W4385570752 creator A5004258058 @default.
- W4385570752 creator A5016622651 @default.
- W4385570752 creator A5031030600 @default.
- W4385570752 date "2023-01-01" @default.
- W4385570752 modified "2023-09-25" @default.
- W4385570752 title "LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning" @default.
- W4385570752 doi "https://doi.org/10.18653/v1/2023.acl-short.59" @default.
- W4385570752 hasPublicationYear "2023" @default.
- W4385570752 type Work @default.
- W4385570752 citedByCount "0" @default.
- W4385570752 crossrefType "proceedings-article" @default.
- W4385570752 hasAuthorship W4385570752A5004258058 @default.
- W4385570752 hasAuthorship W4385570752A5016622651 @default.
- W4385570752 hasAuthorship W4385570752A5031030600 @default.
- W4385570752 hasBestOaLocation W43855707521 @default.
- W4385570752 hasConcept C104317684 @default.
- W4385570752 hasConcept C105580179 @default.
- W4385570752 hasConcept C119857082 @default.
- W4385570752 hasConcept C121332964 @default.
- W4385570752 hasConcept C137293760 @default.
- W4385570752 hasConcept C149364088 @default.
- W4385570752 hasConcept C154945302 @default.
- W4385570752 hasConcept C157524613 @default.
- W4385570752 hasConcept C167966045 @default.
- W4385570752 hasConcept C185592680 @default.
- W4385570752 hasConcept C204321447 @default.
- W4385570752 hasConcept C39890363 @default.
- W4385570752 hasConcept C41008148 @default.
- W4385570752 hasConcept C55493867 @default.
- W4385570752 hasConcept C62520636 @default.
- W4385570752 hasConceptScore W4385570752C104317684 @default.
- W4385570752 hasConceptScore W4385570752C105580179 @default.
- W4385570752 hasConceptScore W4385570752C119857082 @default.
- W4385570752 hasConceptScore W4385570752C121332964 @default.
- W4385570752 hasConceptScore W4385570752C137293760 @default.
- W4385570752 hasConceptScore W4385570752C149364088 @default.
- W4385570752 hasConceptScore W4385570752C154945302 @default.
- W4385570752 hasConceptScore W4385570752C157524613 @default.
- W4385570752 hasConceptScore W4385570752C167966045 @default.
- W4385570752 hasConceptScore W4385570752C185592680 @default.
- W4385570752 hasConceptScore W4385570752C204321447 @default.
- W4385570752 hasConceptScore W4385570752C39890363 @default.
- W4385570752 hasConceptScore W4385570752C41008148 @default.
- W4385570752 hasConceptScore W4385570752C55493867 @default.
- W4385570752 hasConceptScore W4385570752C62520636 @default.
- W4385570752 hasLocation W43855707521 @default.
- W4385570752 hasLocation W43855707522 @default.
- W4385570752 hasOpenAccess W4385570752 @default.
- W4385570752 hasPrimaryLocation W43855707521 @default.
- W4385570752 hasRelatedWork W1534961803 @default.
- W4385570752 hasRelatedWork W2100833569 @default.
- W4385570752 hasRelatedWork W2359001871 @default.
- W4385570752 hasRelatedWork W3015697211 @default.
- W4385570752 hasRelatedWork W3165012362 @default.
- W4385570752 hasRelatedWork W3165571652 @default.
- W4385570752 hasRelatedWork W4303649048 @default.
- W4385570752 hasRelatedWork W4309397537 @default.
- W4385570752 hasRelatedWork W4311978828 @default.
- W4385570752 hasRelatedWork W2310403681 @default.
- W4385570752 isParatext "false" @default.
- W4385570752 isRetracted "false" @default.
- W4385570752 workType "article" @default.