5 papers · 1 filter
A New Pair of GloVes
Riley Carlson, John Bauer, Christopher D. Manning
This report documents, describes, and evaluates new 2024 English GloVe (Global Vectors for Word Representation) models. While the original GloVe models built in 2014 have been wide…
Drop Dropout on Single-Epoch Language Model Pretraining
Houjun Liu, John Bauer, Christopher D. Manning
Originally, dropout was seen as a breakthrough regularization technique that reduced overfitting and improved performance in almost all applications of deep learning by reducing ov…
Osiris: A Lightweight Open-Source Hallucination Detection System
Alex Shan, John Bauer, Christopher D. Manning
Retrieval-Augmented Generation (RAG) systems have gained widespread adoption by application builders because they leverage sources of truth to enable Large Language Models (LLMs) t…
Semgrex and Ssurgeon, Searching and Manipulating Dependency Graphs
John Bauer, Chloe Kiddon, Eric Yeh +2
Searching dependency graphs and manipulating them can be a time consuming and challenging task to get right. We document Semgrex, a system for searching dependency graphs, and intr…
Do "English" Named Entity Recognizers Work Well on Global Englishes?
Alexander Shan, John Bauer, Riley Carlson +1
The vast majority of the popular English named entity recognition (NER) datasets contain American or British English data, despite the existence of many global varieties of English…