Общественный бенчмарк

material ID: publicbenchmark

Related Papers

Phrase-aware Unsupervised Constituency Parsing

Authors: nan

Publication: TIPSTER (2022)

DOI: nan

AbstractRecent studies have achieved inspiring success in unsupervised grammar induction using masked language modeling (MLM) as the proxy task. Despite their high accuracy in identifying low-level structures, prior arts tend …...

38943

ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

Authors: nan

Publication: TIPSTER (2023)

DOI: nan

AbstractLarge pre-trained language models achieve impressive results across many tasks. However, recent works point out that pre-trained language models may memorize a considerable fraction of their training data, leading to …...

37876