Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Banyan: Improved Representation Learning with Explicit Structure
Mattia Opper, N. Siddharth
We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-r…
cs.CL2023
On the effect of curriculum learning with developmental data for grammar acquisition
Mattia Opper, J. Morrison, N. Siddharth
This work explores the degree to which grammar acquisition is driven by language `simplicity' and the source modality (speech vs. text) of data. Using BabyBERTa as a probe, we find…