Saved in:
Bibliographic Details
Main Authors: Opper, Mattia, Siddharth, N.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.17771
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-resource settings. Conversely recent structured models have shown promise as efficient learners, but lack performance. Banyan bridges this gap with two key innovations: an entangled hierarchical tree structure and diagonalized message passing, enabling it to outperform larger transformer models with just 14 non-embedding parameters. It excels in low-resource settings, offering a viable alternative for under-represented languages and highlighting its potential for efficient, interpretable NLP in resource-constrained environments.