← Search

Slav Petrov

2 accepted papers

2023

Transcending Scaling Laws with 0.1% Extra Compute

EMNLP 2023long main

Scaling language models improves performance but comes with significant computational costs. This paper proposes UL2R, a method that substantially improves existing language models and their scaling curves with a relatively tiny amount of extra compute. The key idea is to continue training a state-o…

Cited by 0SourceScholar
2015

Grammar as a Foreign Language

NeurIPS 2015poster

Syntactic constituency parsing is a fundamental problem in naturallanguage processing which has been the subject of intensive researchand engineering for decades. As a result, the most accurate parsersare domain specific, complex, and inefficient. In this paper we showthat the domain agnostic atte…

Cited by 1170SourcePDFScholar