Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380989810> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4380989810 abstract "Few-shot learning-the ability to train models with access to limited data-has become increasingly popular in the natural language processing (NLP) domain, as large language models such as GPT and T0 have been empirically shown to achieve high performance in numerous tasks with access to just a handful of labeled examples. Smaller language models such as BERT and its variants have also been shown to achieve strong performance with just a handful of labeled examples when combined with few-shot learning algorithms like pattern-exploiting training (PET) and SetFit. The focus of this work is to investigate the performance of alternative few-shot learning approaches with BERT-based models. Specifically, vanilla fine-tuning, PET and SetFit are compared for numerous BERT-based checkpoints over an array of training set sizes. To facilitate this investigation, applications of few-shot learning are considered in software engineering. For each task, high-performance techniques and their associated model checkpoints are identified through detailed empirical analysis. Our results establish PET as a strong few-shot learning approach, and our analysis shows that with just a few hundred labeled examples it can achieve performance near that of fine-tuning on full-sized data sets." @default.
- W4380989810 created "2023-06-17" @default.
- W4380989810 creator A5031741456 @default.
- W4380989810 creator A5037002753 @default.
- W4380989810 creator A5070091996 @default.
- W4380989810 date "2023-06-13" @default.
- W4380989810 modified "2023-09-26" @default.
- W4380989810 title "Few-shot learning for sentence pair classification and its applications in software engineering" @default.
- W4380989810 doi "https://doi.org/10.48550/arxiv.2306.08058" @default.
- W4380989810 hasPublicationYear "2023" @default.
- W4380989810 type Work @default.
- W4380989810 citedByCount "0" @default.
- W4380989810 crossrefType "posted-content" @default.
- W4380989810 hasAuthorship W4380989810A5031741456 @default.
- W4380989810 hasAuthorship W4380989810A5037002753 @default.
- W4380989810 hasAuthorship W4380989810A5070091996 @default.
- W4380989810 hasBestOaLocation W43809898101 @default.
- W4380989810 hasConcept C119857082 @default.
- W4380989810 hasConcept C120665830 @default.
- W4380989810 hasConcept C121332964 @default.
- W4380989810 hasConcept C127413603 @default.
- W4380989810 hasConcept C134306372 @default.
- W4380989810 hasConcept C154945302 @default.
- W4380989810 hasConcept C177264268 @default.
- W4380989810 hasConcept C178790620 @default.
- W4380989810 hasConcept C185592680 @default.
- W4380989810 hasConcept C192209626 @default.
- W4380989810 hasConcept C199360897 @default.
- W4380989810 hasConcept C201995342 @default.
- W4380989810 hasConcept C204321447 @default.
- W4380989810 hasConcept C2777530160 @default.
- W4380989810 hasConcept C2777904410 @default.
- W4380989810 hasConcept C2778344882 @default.
- W4380989810 hasConcept C2780451532 @default.
- W4380989810 hasConcept C33923547 @default.
- W4380989810 hasConcept C36503486 @default.
- W4380989810 hasConcept C41008148 @default.
- W4380989810 hasConcept C51632099 @default.
- W4380989810 hasConceptScore W4380989810C119857082 @default.
- W4380989810 hasConceptScore W4380989810C120665830 @default.
- W4380989810 hasConceptScore W4380989810C121332964 @default.
- W4380989810 hasConceptScore W4380989810C127413603 @default.
- W4380989810 hasConceptScore W4380989810C134306372 @default.
- W4380989810 hasConceptScore W4380989810C154945302 @default.
- W4380989810 hasConceptScore W4380989810C177264268 @default.
- W4380989810 hasConceptScore W4380989810C178790620 @default.
- W4380989810 hasConceptScore W4380989810C185592680 @default.
- W4380989810 hasConceptScore W4380989810C192209626 @default.
- W4380989810 hasConceptScore W4380989810C199360897 @default.
- W4380989810 hasConceptScore W4380989810C201995342 @default.
- W4380989810 hasConceptScore W4380989810C204321447 @default.
- W4380989810 hasConceptScore W4380989810C2777530160 @default.
- W4380989810 hasConceptScore W4380989810C2777904410 @default.
- W4380989810 hasConceptScore W4380989810C2778344882 @default.
- W4380989810 hasConceptScore W4380989810C2780451532 @default.
- W4380989810 hasConceptScore W4380989810C33923547 @default.
- W4380989810 hasConceptScore W4380989810C36503486 @default.
- W4380989810 hasConceptScore W4380989810C41008148 @default.
- W4380989810 hasConceptScore W4380989810C51632099 @default.
- W4380989810 hasLocation W43809898101 @default.
- W4380989810 hasOpenAccess W4380989810 @default.
- W4380989810 hasPrimaryLocation W43809898101 @default.
- W4380989810 hasRelatedWork W1567338489 @default.
- W4380989810 hasRelatedWork W159132833 @default.
- W4380989810 hasRelatedWork W1978971213 @default.
- W4380989810 hasRelatedWork W2081647779 @default.
- W4380989810 hasRelatedWork W2369835347 @default.
- W4380989810 hasRelatedWork W2972743339 @default.
- W4380989810 hasRelatedWork W3092800243 @default.
- W4380989810 hasRelatedWork W3119254911 @default.
- W4380989810 hasRelatedWork W3185852197 @default.
- W4380989810 hasRelatedWork W4287639816 @default.
- W4380989810 isParatext "false" @default.
- W4380989810 isRetracted "false" @default.
- W4380989810 workType "article" @default.