Saved in:
Bibliographic Details
Main Authors: Gonzalez-Gutierrez, Cesar, Quattoni, Ariadna
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.24455
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915313535156224
author Gonzalez-Gutierrez, Cesar
Quattoni, Ariadna
author_facet Gonzalez-Gutierrez, Cesar
Quattoni, Ariadna
contents This empirical study analyzes the effects of the pre-training corpus on the quality of learned transformer representations. We focus on the representation quality induced solely through pre-training. Our experiments show that pre-training on a small, specialized corpus can yield effective representations, and that the success of combining a generic and a specialized corpus depends on the distributional similarity between the target task and the specialized corpus.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Domain Pre-training Impact on Representations
Gonzalez-Gutierrez, Cesar
Quattoni, Ariadna
Computation and Language
This empirical study analyzes the effects of the pre-training corpus on the quality of learned transformer representations. We focus on the representation quality induced solely through pre-training. Our experiments show that pre-training on a small, specialized corpus can yield effective representations, and that the success of combining a generic and a specialized corpus depends on the distributional similarity between the target task and the specialized corpus.
title Domain Pre-training Impact on Representations
topic Computation and Language
url https://arxiv.org/abs/2505.24455