Different Tokenization Schemes Lead to Comparable Performance in Spanish Number Agreement

The relationship between language model tokenization and performance is an open area of research. Here, we investigate how different tokenization schemes impact number agreement in Spanish plurals. We find that morphologically-aligned tokenization performs similarly to other tokenization schemes, ev...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Arnett, Catherine, Rivière, Pamela D, Chang, Tyler A, Trott, Sean
Format: Article
Language:English
Subjects:
Morphology
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The relationship between language model tokenization and performance is an open area of research. Here, we investigate how different tokenization schemes impact number agreement in Spanish plurals. We find that morphologically-aligned tokenization performs similarly to other tokenization schemes, even when induced artificially for words that would not be tokenized that way during training. We then present exploratory analyses demonstrating that language model embeddings for different plural tokenizations have similar distributions along the embedding space axis that maximally distinguishes singular and plural nouns. Our results suggest that morphologically-aligned tokenization is a viable tokenization approach, and existing models already generalize some morphological patterns to new items. However, our results indicate that morphological tokenization is not strictly required for performance.
ISSN:2331-8422