1

Linear Connectivity Reveals Generalization Strategies
It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they …
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra
URL
Linear Connectivity Reveals Generalization Strategies
Benchmarking Compositionality with Formal Languages
Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large …
Josef Valvoda, Naomi Saphra, Jonathan Rawski, Adina Williams, Ryan Cotterell
PDF
A Non-Linear Structural Probe
Probes are models devised to investigate the encoding of knowledge{—}e.g. syntactic structure{—}in contextual …
Jennifer C White, Tiago Pimentel, Naomi Saphra, Ryan Cotterell
PDF
The MultiBERTs: BERT Reproductions for Robustness Analysis
Experiments with pre-trained models such as BERT are often based on a single checkpoint. While the conclusions drawn apply to the …
Thibault Sellam, Steve Yadlowsky, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Turc, Jacob Eisenstein, Dipanjan Das, Ian Tenney, Ellie Pavlick
PDF
Understanding Privacy-Related Questions on Stack Overflow
Mohammad Tahaei, Kami Vaniea, Naomi Saphra
PDF
LSTMs Compose (and Learn) Bottom-Up
Recent work in NLP shows that LSTM language models capture hierarchical structure in language data. In contrast to existing work, we …
Naomi Saphra, Adam Lopez
PDF
Pareto Probing: Trading Off Accuracy for Complexity
The question of how to probe contextual word representations in a way that is principled and useful has seen significant recent …
Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell
PDF
Understanding Learning Dynamics Of Language Models with SVCCA
Research has shown that neural models implicitly encode linguistic features, but there has been no research showing how these encodings …
Naomi Saphra, Adam Lopez
PDF
AMRICA: an AMR Inspector for Cross-language Alignments
Abstract Meaning Representation (AMR), an annotation scheme for natural language semantics, has drawn attention for its simplicity and …
Naomi Saphra, Adam Lopez
PDF
Understanding Objects in Detail with Fine-grained Attributes
A. Vedaldi, S. Mahendran, S. Tsogkas, S. Maji, B. Girshick, J. Kannala, E. Rahtu, I. Kokkinos, M. B. Blaschko, D. Weiss, B. Taskar, K. Simonyan, Naomi Saphra, S. Mohamed
PDF