all AI news
Improving language models fine-tuning with representation consistency targets. (arXiv:2205.11603v1 [cs.CL])
May 25, 2022, 1:11 a.m. | Anastasia Razdaibiedina, Vivek Madan, Zohar Karnin, Ashish Khetan, Vishaal Kapoor
cs.CL updates on arXiv.org arxiv.org
Fine-tuning contextualized representations learned by pre-trained language
models has become a standard practice in the NLP field. However, pre-trained
representations are prone to degradation (also known as representation
collapse) during fine-tuning, which leads to instability, suboptimal
performance, and weak generalization. In this paper, we propose a novel
fine-tuning method that avoids representation collapse during fine-tuning by
discouraging undesirable changes in the representations. We show that our
approach matches or exceeds the performance of the existing
regularization-based fine-tuning methods across 13 …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Vice President, Data Science, Marketplace
@ Xometry | North Bethesda, Maryland, Lexington, KY, Remote
Field Solutions Developer IV, Generative AI, Google Cloud
@ Google | Toronto, ON, Canada; Atlanta, GA, USA